M.Sc.

Artificial Intelligence
and Machine Learning (PO
2023)
Module Handbook
FB 20 - Department of Computer Science
Date: 01.09.2023

INFORMATION:
This translation is not an official document. It is a service for our
international students and prospective students.

The English translation is for information purpose only.

The legally binding document is the German version.
Module Handbook: M.Sc. Artificial Intelligence and Machine Learning (PO 2023)

Date: 01.09.2023

FB 20 - Department of Computer Science

II
Contents

1 Elective Areas and Studium Generale 1

1.1 Elective Areas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1.1 Technical Examinations from the Elective Areas of the M.Sc. Artificial Intelligence and Machine
Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1.1.1 Foundations of Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Causality for Artificial Intelligence and Machine Learning . . . . . . . . . . . . . . . . . . 1
Deep Learning: Architectures & Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Introduction to Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Probabilistic Graphical Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Reinforcement Learning: From Foundations to Deep Approaches . . . . . . . . . . . . . . 9
Statistical Relational Artificial Intelligence: Logic, Probability, and Computation . . . . . 11
Statistical Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
1.1.1.2 AI Models and Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
Data Mining and Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
Deep Learning for Medical Imaging . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
Deep Learning for Natural Language Processing . . . . . . . . . . . . . . . . . . . . . . . 18
Information Theory I: Fundaments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
Continual Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
Robot Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
Model Checking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
Optimization of static and dynamic systems . . . . . . . . . . . . . . . . . . . . . . . . . 26
Optimization Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
Deep Generative Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
1.1.1.3 AI Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
Advanced Data Management Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
Analysis of Hybrid Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
Automated Theorem Proving . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
Concepts and Technologies for Distributed Systems and Big Data Processing . . . . . . . 34
Scalable Data Management Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
1.1.1.4 AI Domains and Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
3D Scanning & Motion Capture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
Ambient Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
Bioinformatics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
Capturing Reality . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
Computer Vision I . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
Computer Vision II . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
Ethics in Natural Language Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49
Foundations of Language Technology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
Foundations of Robotics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
Intelligent Robotic Manipulation: Advanced topics in Robot Perception, Planning and Control 55
Learning and Educational Technologies . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
Human and Identity centric Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . 59
Model Predictive Control and Machine Learning . . . . . . . . . . . . . . . . . . . . . . . 61
Natural Language Processing and the Web . . . . . . . . . . . . . . . . . . . . . . . . . . 63
Technology transfer and entrepreneurship with a focus on artificial intelligence . . . . . . 65

III
 1.1.2 Study-related Achievements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66
1.1.2.1 Seminars . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66
Recent Topics in the Development and Application of Modern Robotic Systems . . . . . . 66
Deep Learning and Digital Humanities . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68
Extended Seminar - Systems and Machine Learning . . . . . . . . . . . . . . . . . . . . . 69
Extended Seminar - AI for Data Management . . . . . . . . . . . . . . . . . . . . . . . . 71
Advanced Topics in Computer Vision and Machine Learning . . . . . . . . . . . . . . . . 73
Humanoid Robotics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75
Intelligent Robotic Manipulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76
Intelligent Robotic Manipulation: Part II . . . . . . . . . . . . . . . . . . . . . . . . . . . 78
Seminar Data Mining and Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . 80
Software Engineering for Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . 82
Symbolic Execution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84
Text Analytics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85
Computational Neuroscience . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86
1.1.2.2 Practical Lab in Teaching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 88
Practical Lab in Teaching - Computational Engineering and Robotics . . . . . . . . . . . . 88
Data Management - Teaching Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89
Teaching Lab - Deep Learning for Natural Language Processing . . . . . . . . . . . . . . 90
Practical Lab in Teaching - Introduction to Artificial Intelligence . . . . . . . . . . . . . . 91
Teaching Lab - Foundations of Language Technology (FOLT) . . . . . . . . . . . . . . . . 93
Teaching Lab - Natural Language Processing . . . . . . . . . . . . . . . . . . . . . . . . . 94
Practical Lab in Teaching - Optimization of Static and Dynamic Systems . . . . . . . . . . 95
Practical Lab in Teaching - Statistical Machine Learning . . . . . . . . . . . . . . . . . . . 96
Teaching Lab - Visual Computing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97
Practical Lab in Teaching - Visual Inference . . . . . . . . . . . . . . . . . . . . . . . . . . 98
Practical Lab in Teaching: Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . 99
1.1.2.3 Labs, Project Labs, Related Courses . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 100
Data Management - Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 100
Data Management - Extended Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 102
Distributed Systems Programming: Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103
Expert Lab on Robot Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105
Research Project Knowledge Engineering and Machine Learning . . . . . . . . . . . . . . 106
Advanced Visual Computing Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108
Integrated Robotics Project 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109
Integrated Robotics Project 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111
Robot Learning: Integrated Project - Part 1 . . . . . . . . . . . . . . . . . . . . . . . . . . 113
Robot Learning: Integrated Project - Part 2 . . . . . . . . . . . . . . . . . . . . . . . . . . 114
Practical Course in Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . 115
Visual Computing Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117
Practical Lab on Intelligent Robot Manipulation . . . . . . . . . . . . . . . . . . . . . . . 118
Lab on intelligent Robotic Manipulation: : Part II . . . . . . . . . . . . . . . . . . . . . . 119
Practical Exercises for Neural Information Processing for Brain-Computer Interfaces . . . 120
Practical Project Knowledge Engineering and Machine Learning . . . . . . . . . . . . . . 121
Project Lab Deep Learning in Computer Vision . . . . . . . . . . . . . . . . . . . . . . . . 123
Project Lab E-Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 124
Robotics Lab Project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 125
Data Analysis Software Project for Natural Language . . . . . . . . . . . . . . . . . . . . 127
1.2 Studium Generale . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128

IV
1 Elective Areas and Studium Generale

1.1 Elective Areas

1.1.1 Technical Examinations from the Elective Areas of the M.Sc. Artificial Intelligence and
Machine Learning

1.1.1.1 Foundations of Artificial Intelligence

Module name
Causality for Artificial Intelligence and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1189 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1189-vl Causality for Artificial Intelligence and 0 Lecture 2
Machine Learning
2 Teaching content
The lecture is structured to provide a comprehensive overview of the many facets of discussing causal modelling
assumptions, formulating the causal query of interest, discerning correlations from causation and inferring the
causal structure and parameterization of interest. Respectively, explored topics include:
• Introduction and motivation to Pearlian causality and causality for AI & ML
• From statistical to causal learning
• The Pearl Causal Hierarchy of observations, interventions and counterfactuals
• Discovering causal relationships
• Structural Causal Models (SCM)
• Learning neurally parameterized SCM
• Common assumptions in the causal inference literature
• Theoretical underpinnings of causality
• Benchmarks for causal inference
• Existing areas of research within the intersection of causality and machine learning
• Open-ended research questions and applications

3 Learning objectives

1
 Understanding causal interactions is central to human cognition and unlocking similar capabilities in machines
is a central new quest in the study of artificial intelligence and machine learning. The Pearlian theory of
causality poses as a key player in the new dawn of intelligent machines through the rigorous formalization of
ideas such as interventions, counterfactuals and structural mechanisms.

Upon successful completion of the module, students will have learned to go beyond the realm of
pure statistics and correlations in the data domain, that ultimately pose an insurmountable wall to modern
techniques like deep learning, and start embracing approaches that make us of modelling assumptions in
order to reason about causal quantities. In addition to a comprehensive overview of the fundamentals of
Pearlian causality and cutting-edge approaches at the intersection of causality with AI & ML, students will
have expanded their knowledge with techniques for causal inference spanning across the hierarchy of causal
reasoning to improve sample efficiency, robustness and generalization capabilities of existing models.
4 Prerequisite for participation
Recommended:

Basic mathematical knowledge on probability theory and statistics is required as covered in the course
"Mathematics III for Computer Science".
Basic machine learning knowledge from at least one or more of the following courses is required: "Statistical
Machine Learning", "Introduction to Artificial Intelligence", "Probabilistic Graphical Models", "Deep Learning",
or one of the several offered Praktika.
Basic knowledge on graphical models is recommended as covered in the course "Probabilistic Graphical
Models".
5 Form of examination
Course related exam:
• [20-00-1189-vl] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1189-vl] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

2
Module name
Deep Learning: Architectures & Methods
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1034 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1034-iv Deep Learning: Architectures & Methods 0 Integrated 4
course
2 Teaching content
• Review of machine learning background
• Deep Feedforward Networks
• Regularization for Deep Learning
• Optimization for Training Deep Models
• Convolutional Networks
• Sequence Modeling: Recurrent and Recursive Nets
• Linear Factor Models
• Autoencoders
• Representation Learning
• Structured Probabilistic Models for Deep Learning
• Monte Carlo Methods
• Approximate Inference
• Deep Generative Models
• Deep Reinforcement Learning
• Deep Learning in Vision
• Deep Learning in NLP
3 Learning objectives
This course provides students with the required advanced background on machine learning the knowledge to
independently carry out research projects on the hot topic of deep learning, e.g. within the scope of a Bachelor's
or Master's thesis. In particular, this class aims at providing the students with fundamental understanding of
deep learning algorithms and the architecture of deep networks.
4 Prerequisite for participation
20-00-0358-iv Statistical Machine Learning
20-00-0052-iv Data Mining and Machine Learning
5 Form of examination
Course related exam:
• [20-00-1034-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1034-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

3
 B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

4
Module name
Introduction to Artificial Intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1058 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1058-iv Introduction to Artificial Intelligence 0 Integrated 3
course
2 Teaching content
Artificial Intelligence (AI) is concerned with algorithms for solving problems, whose solution is generally
assumed to require intelligence. While research in the early days was oriented on results about human thinking,
the field has since developed towards solutions that try to exploit the strengths of the computer. In the course of
this lecture we will give a brief survey over key topics of this core discipline of computer science, with a particular
focus on the topics search, planning, learning, and reasoning. Historical and philosophical foundations will
also be considered.
• Foundations
• Introduction, History of AI (RN chapter 1)
• Intelligent Agents (RN chapter 2)
• Search
• Uninformed Search (RN chapters 3.1 - 3.4)
• Heuristic Search (RN chapters 3.5, 3.6)
• Local Search (RN chapter 4)
• Constraint Satisfaction Problems (RN chapter 6)
• Games: Adversarial Search (RN chapter 5)
• Planning
• Planning in State Space (RN chapter 10)
• Planning in Plan Space (RN chapter 11)
• Decisions under Uncertainty
• Uncertainty and Probabilities (RN chapter 13)
• Bayesian Networks (RN chapter 14)
• Decision Making (RN chapter 16)
• Machine Learning
• Neural Networks (RN chapters 18.1,18.2,18.7)
• Reinforcement Learning (RN chapter 21)
• Philosophical Foundations

3 Learning objectives
After a successful completion of this module, students are in a position to
• understand and explain fundemental techniques of artificial intelligence
• participate in a discussion about the possibility of an artificial intelligence with well-founded arguments
• critically judge new developments in this area

4 Prerequisite for participation

5 Form of examination

5
 Course related exam:
• [20-00-1058-iv] (Technical examination, Oral/written examination, Default RS)
Written Exam (90 min.)
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1058-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Autonome Systeme und Robotik
M.Sc. Artificial Intelligence and Machine Learning

May be used in other degree programs.

9 References

10 Comment

6
Module name
Probabilistic Graphical Models
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0449 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Ph. D. Stefan Roth
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0449-iv Probabilistic Graphical Models 0 Integrated 4
course
2 Teaching content
- Refresher of probability & Bayesian decision theory
- Directed and undirected models and their properties
- Inference in tree graphs
- Approximate inference in general graphs: Message passing and mean field
- Learning of directed and undirected models
- Sampling methods for learning and inference
- Modeling in example applications, including topic models
- Deep networks
- Semi-supervised learning
3 Learning objectives
After successfully attending the course, students have developed an in-depth understanding of probabilistic
graphical models. They describe and analyze properties of graphical models, and formulate suitable models
for concrete estimation and learning tasks. They understand inference algorithms, judge their suitability and
apply them to graphical models in relevant applications. Moreover, they determine which learning algorithms
are suitable to estimate the model parameters from example data, and apply these.
4 Prerequisite for participation
Recommended: Participation in “Statistisches Maschinelles Lernen”.
5 Form of examination
Course related exam:
• [20-00-0449-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0449-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

7
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Literature recommendations will be updated regularly, an example might be:
- D. Barber: “Bayesian Reasoning and Machine Learning”, Cambridge University Press 2012
- D. Koller, N. Friedman: “Probabilistic Graphical Models: Principles and Techniques”, MIT Press 2009
10 Comment

8
Module name
Reinforcement Learning: From Foundations to Deep Approaches
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1047 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1047-iv Reinforcement Learning: From Founda- 0 Integrated 4
tions to Deep Approaches course
2 Teaching content
• Review of machine learning background
• Black box Reinforcement Learning
• Modeling as bandit, Markov Decision Processes and Partially Observable Markov Decision Processes
• Optimal control
• System identification
• Learning value functions
• Policy search
• Deep value functions methods
• Deep policy search methods
• Exploration vs exploitation
• Hierarchical reinforcement learning
• Intrinsic motivation
3 Learning objectives
This course provides students with the required basic background on machine learning the knowledge to
independently carry out research projects on the hot topic of reinforcement learning, e.g. within the scope
of a Bachelor's or Master's thesis. In particular, this class aims at providing the students with fundamental
understanding of reinforcement learning algorithms and the application within deep learning.
4 Prerequisite for participation
Good programming in Python.
Lecture Statistical Machine Learning is helpful but not mandatory.
5 Form of examination
Course related exam:
• [20-00-1047-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1047-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

9
10
Module name
Statistical Relational Artificial Intelligence: Logic, Probability, and Computation
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1011 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1011-iv Statistical Relational Artificial Intelli- 0 Integrated 4
gence: Logic, Probability, and Computa- course
tion
2 Teaching content
+ Logic programming
+ Inductive logic programming, i.e., learning logical programs from data
+ Probabilistic graphical models: Inference and Learning
+ Statistical relational models such as ProbLog and Markov logic networks
+ Inference within statistical relational models
+ Learning statistical relational models from data
+ Relational linear and quadratic programs
3 Learning objectives
The lecture provides a systematic introduction to the foundations and methods of statistical relational learning
and AI: the study and design of intelligent agents that act in worlds composed of individuals (objects, things),
where there can be complex relations among the individuals, where the agents can be uncertain about what
properties individuals have, what relations are true, what individuals exist, whether different terms denote
the same individual, and the dynamics of the world. After the successful completion of the course, students
understand the basic concepts and methods of statistical relational AI. They understand the basic challenges
posed by relational domains and know the current state of the art to meet tem. They are able to apply the
acquired toolbox to novel problems.
4 Prerequisite for participation
The successful completion of “Statistical Machine Learning” and of “Probabilistic Graphical Models” is recom-
mended but not required.
5 Form of examination
Course related exam:
• [20-00-1011-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1011-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

11
 Pointers to literature will be updated regularly and include:

Luc De Raedt, Kristian Kersting, Sriraam Natarajan, David Poole (2016): Statistical Relational Artifi-
cial Intelligence: Logic, Probability, and Computation. Synthesis Lectures on Artificial Intelligence and Machine
Learning, Morgan & Claypool Publishers, ISBN: 9781627058414.
10 Comment

12
Module name
Statistical Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0358 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Kristian Kersting
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0358-iv Statistical Machine Learning 0 Integrated 4
course
2 Teaching content
- Statistical Methods for Machine Learning
- Refreshers on Statistics, Optimization and Linear Algebra
- Bayes Decision Theory
- Probability Density Estimation
- Non-Parametric Models
- Mixture Models and EM-Algorithms
- Linear Models for Classification and Regression
- Statistical Learning Theory
- Kernel Methods for Classification and Regression
3 Learning objectives
The lecture gives a systematic introduction to statistical methods for machine learning. Upon successful
completion of this lecture, students will understand the most important methods and approaches of statistical
machine learning. They can apply machine learning to solve various new problems.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-0358-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0358-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

13
9 References
1. C.M. Bishop, Pattern Recognition and Machine Learning (2006), Springer
2. K.P. Murphy, Machine Learning: a Probabilistic Perspective (expected 2012), MIT Press
3. D. Barber, Bayesian Reasoning and Machine Learning (2012), Cambridge University Press
4. T. Hastie, R. Tibshirani, and J. Friedman (2003), The Elements of Statistical Learning, Springer Verlag
5. D. MacKay, Information Theory, Inference, and Learning Algorithms (2003), Cambridge University Press
6. R.O. Duda, P.E. Hart, and D.G. Stork, Pattern Classification (2nd ed. 2001), Willey-Interscience
7. T.M. Mitchell, Machine Learning (1997), McGraw-Hill
10 Comment

14
1.1.1.2 AI Models and Methods

Module name
Data Mining and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0052 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0052-iv Data Mining and Machine Learning 0 Integrated 4
course
2 Teaching content
With the rapid development of information technology bigger and bigger amounts of data are available. These
often contain implicit knowledge, which, if it were known, could have significant commercial or scientific value.
Data Mining is a research area that is concerned with the search for potentially useful knowledge in large data
sets, and machine learning is one of the key techniques in this area.

This course offers an introduction into the area of machine learning from the angle of data mining.
Different techniques from various paradigms of machine learning will be introduced with exemplary
applications. To operationalize this knowledge, a practical part of the course is concerned with the use of data
mining tools in applications.
• Introduction (Foundation, Learning problems, Concepts, Examples, Representation)
• Rule Learning
– Learning of indivicual rules (generalization vs. specialization, structured hypothesis spaces, version
spaces)
– Learning of rule sets (covering strategy, evaluation measures for rules, pruning, multi-class problems)
• Evaluation and cost-sensitive Learning (Accuracy, X-Val, ROC Curves, Cost-Sensitive Learning)
• Instance-Based Learning (kNN, IBL, NEAR, RISE)
• Decision Tree Learning (ID3, C4.5, etc.)
• Ensemble Methods (Bias/Variance, Bagging, Randomization, Boosting, Stacking, ECOCs)
• Pre-Processing (Feature Subset Selection, Discretization, Sampling, Data Cleaning)
• Clustering and Learning of Association Rules (Apriori)"

3 Learning objectives
After a successful completion of this module, students are in a position to
- understand and explain fundemental techniques of data mining and machine learning
- apply practical data mining systems and understand their strengths and limitations
- critically judge new developments in this area
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-0052-iv] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.

Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).

15
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0052-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B. Sc. Informatik
M. Sc. Informatik
M. Sc. Computer Science
M. Sc. Autonome Systeme und Robotik
M. Sc. Artificial Intelligence and Machine Learning
M. Sc. IT Sicherheit

May be used in other degree programs.

9 References
- Mitchell: Machine Learning, McGraw-Hill, 1997
- Ian H. Witten and Eibe Frank: Data Mining: Practical Machine Learning Tools and Techniques with Java
Implementations, Morgan-Kaufmann, 1999
10 Comment

16
Module name
Deep Learning for Medical Imaging
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1014 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr.-Ing. Michael Gösele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1014-iv Deep Learning for Medical Imaging 0 Integrated 3
course
2 Teaching content
Formulating Medical Image Segmentation, Computer Aided Diagnosis and Surgical Planning as Machine
Learning Problems, Deep Learning for Medical Image Segmentation, Deep Learning for Computer Aided
Diagnosis, Surgical Planning from pre-surgical images using Deep Learning, Tool presence detection and
localization from endoscopic videos using Deep learning, Adversarial Examples for Medical Imaging, Generative
Adversarial Networks for Medical Imaging.
3 Learning objectives
After successful completion of the course, students should be able to understand all components of formulating
a Medical Image Analysis problem as a Machine Learning problem. They should also be able to make informed
decision of choosing a general purpose deep learning paradigm for given medical image analysis problem.
4 Prerequisite for participation
- Programming skills
- Understanding of Algorithmic design
- Linear Algebra
- Image Processing / Computer Vision I
- Statistical Machine Learning
5 Form of examination
Course related exam:
• [20-00-1014-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1014-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

17
Module name
Deep Learning for Natural Language Processing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0947 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0947-iv Deep Learning for Natural Language Pro- 0 Integrated 4
cessing course
2 Teaching content
The lecture provides an introduction to the foundational concepts of deep learning and their application to
problems in the area of natural language processing (NLP)
Main content:
- foundations of deep learning (e.g. feed-forward networks, hidden layers, backpropagation, activation functions,
loss functions)
- word embeddings: theory, different approaches and models, application as features for machine learning
- different architectures of neuronal networks (e.g. recurrent NN, recursive NN, convolutional NN) and their
application for groups of NLP problems such as document classification (e.g. spam detection), sequence labeling
(e.g. POS-tagging, Named Entity Recognition) and more complex structure prediction (e.g. Chunking, Parsing,
Semantic Role Labeling)
3 Learning objectives
After completion of the lecture, the students are able to
- explain the basic concepts of neural networks and deep learning.
- explain the concept of word embeddings, train word embeddings and use them for solving NLP problems.
- understand and describe neural network architectures that are used to tackle classical NLP problems such as
classification, sequence prediction, structure prediction.
- implement neural networks for NLP problems using existing libraries in Python.
4 Prerequisite for participation
Basic knowledge of mathematics and programming
5 Form of examination
Course related exam:
• [20-00-0947-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0947-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

18
Module name
Information Theory I: Fundaments
Module nr. Credit points Workload Self-study Module duration Module cycle
18-kp-1010 6 CP 180 h 120 h 1 Term Winter term
Language Module owner
English Prof. Dr. techn. Heinz Köppl
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
18-kp-1010-vl Information Theory I: Fundaments 0 Lecture 3
18-kp-1010-ue Information Theory I: Fundaments 0 Practice 1
2 Teaching content
This lecture course introduces the fundamentals of information theory, network information theory and coding
theory.
Outline:
information, uncertainty, entropy, mutual information, capacity, differential entropy, typical sequences, Gaussian
channels, basics of source and channel coding, linear block codes, Shannon's source coding theorem, Shannon's
channel coding theorem, capacity of Gaussian channels, capacity of bandlimited channels, Shannon's bound,
bandwidth efficiency, capacity of multiple parallel channels and waterfilling, Gaussian vector channel, Multiple
Access Channel, Broadcast Channel, rate region.
3 Learning objectives
Upon completion of the module, students will have an understanding of the fundamentals of classic information
theory.
4 Prerequisite for participation
Recommended: Basic knowledge of probability theory
5 Form of examination
Module exam:
• Module exam (Technical examination, Examination, Duration: 120 Min., Default RS)

6 Prerequisite for the award of credit points

Passing the final module examination
7 Grading
Module exam:
• Module exam (Technical examination, Examination, Weighting: 100 %)

8 Usability of the module

BSc ETiT, BSc iST, MSc iCE, BSc Wi-ETiT, BSc/MSc CE
9 References

1. T.M. Cover and J.A. Thomas, Elements of Information Theory, Wiley & Sons, 1991.
2. R. W. Yeung, Information Theory and Network Coding, Springer, 2008.
3. Abbas El Gamal and Young-Han Kim, Network Information Theory, Cambrige, 2011.

10 Comment

19
Module name
Continual Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1135 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Arjan Kuijper
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1135-vl Continual Machine Learning 0 Lecture 2
2 Teaching content
The course is structured to provide a comprehensive overview of the many facets involved in design, training,
and evaluation of continually evolving systems. Respectively explored topics include:
• Introduction and motivation to learning continually
• From domain adaptation and transfer to continual learning
• Alleviating catastrophic forgetting: methodologies and examples
• Active learning: selecting future data
• Modular and dynamic architectures
• Curriculum learning
• Closed and open world assumptions
• Continual learning benchmarks and metrics
• Learning to learn: a meta-learning perspective
• Software developments for continual learning
• Open-ended research questions and applications

3 Learning objectives
Machine learning studies the design of models and training algorithms in order to learn how to solve tasks from
data. Whereas historically machine learning has concentrated primarily on static predefined training datasets
and respective test scenarios, recent advances also take into account the fact that the world is constantly evolving.
Upon successful completion of the module, students will have learned to go beyond the train-validate-test
phase and embrace modern approaches to machines that can learn continually. In addition to a comprehensive
overview of the breath of factors to consider in continual learning, students will have expanded their knowledge
with techniques that span mitigation of forgetting across multiple tasks, selection of new data in continuous
training, dynamic model architectures, and robustness with respect to unexpected data inputs.
4 Prerequisite for participation
Basic machine learning knowledge from at least one of the following courses is recommended: statistical
machine learning, introduction to artificial intelligence, probabilistic graphical models, deep learning, or one of
the several offered Praktika.
5 Form of examination
Course related exam:
• [20-00-1135-vl] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.

Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading

20
 Course related exam:
• [20-00-1135-vl] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

21
Module name
Robot Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0629 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0629-vl Robot Learning 0 Lecture 4
2 Teaching content
- Foundations from robotics and machine learning for robot learning
- Learning of forward models
- Representation of a policy, hierarchical abstraction wiith movement primitives
- Imitation learning
- Optimal control with learned forward models
- Reinforcement learning and policy search
- Inverse reinforcement learning
3 Learning objectives
Upon successful completion of this course, students are able to understand the relevant foundations of machine
learning and robotics. They will be able to use machine learning approaches to empower robots to learn new
tasks. They will understand the foundations of optimal decision making and reinforcement learning and can
apply reinforcement learning algorithms to let a robot learn from interaction with its environment. Students
will understand the difference between Imitation Learning, Reinforcement Learning, Policy Search and Inverse
Reinforcement Learning and can apply each of this approaches in the appropriate scenario.
4 Prerequisite for participation
Good programming in Matlab
Lecture Machine Learning 1 - Statistical Approaches is helpful but not mandatory.
5 Form of examination
Course related exam:
• [20-00-0629-vl] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0629-vl] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

22
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Deisenroth, M. P.; Neumann, G.; Peters, J. (2013). A Survey on Policy Search for Robotics, Foundations and
Trends in Robotics
Kober, J; Bagnell, D.; Peters, J. (2013). Reinforcement Learning in Robotics: A Survey, International Journal of
Robotics Research
C.M. Bishop, Pattern Recognition and Machine Learning (2006),
R. Sutton, A. Barto. Reinforcement Learning - an Introduction
Nguyen-Tuong, D.; Peters, J. (2011). Model Learning in Robotics: a Survey
10 Comment

23
Module name
Model Checking
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1115 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr.-Ing. Ermira Mezini
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1115-iv Model Checking 0 Lecture 4
2 Teaching content

• Temporal logics
– Linear temporal logic (LTL), Computation tree logic (CTL) und CTL*: syntax, sematics, complexity
• Model checking LTL, CTL und CTL*
• Partial order reduction
• Timed automata

3 Learning objectives
In this module students acquire
• Knowledge of the theoretical foundations of LTL, CTL and CTL*
• Ability to choose a suitable logic for specification and model checking by taking into consideration the
system to be modelled and the kind of properties to be checked
• Knowledge about different model checking techniques like model checking using Büchi automata, partial
order reduction and more
• Knowledge about characteristics and limitations of model checking
• Knowledge in model checking of timed automata
• Ability to use model checker tools

4 Prerequisite for participation

Recommended is knowledge about
• propositional logic
• deduction systems
• automata theory

5 Form of examination
Course related exam:
• [20-00-1115-iv] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1115-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

24
 B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

25
Module name
Optimization of static and dynamic systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0186 10 CP 300 h 210 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0186-iv Optimization of static and dynamic sys- 0 Integrated 6
tems course
2 Teaching content
optimization for static systems:
- unconstrained and constrained nonlinear optimization, optimality conditions
- numerical Newton type and SQP methods
- nonlinear least squares
- gradient free optimization methods
- practical aspects like problem formulation, approximation of derivatives, method specific parameters,
assessment of a computed solution

optimization for dynamic systems:

- parameter optimization and estimation problems
- optimal control problem
- maximum principle and optimality conditions
- numerical methods for computing optimal trajectories
- optimal feedback control
- linear quadratic regulator

applications and case studies from engineering sciences and robotics

theoretical and practical assignments as well as programming tasks for deepening of knowledge and
methodological skills
3 Learning objectives
Through successful participation students acquire fundamental knowledge and methodological skills in concepts,
techniques and computational methods of optimization for static and dynamic systems and their application
for optimization problems in engineering sciences.
4 Prerequisite for participation
grundlegende mathematische Kenntnisse und Fähigkeiten in Linearer Algebra, Analysis mehrerer Veränderlicher
und Grundlagen gewöhnlicher Differentialgleichungen
5 Form of examination
Course related exam:
• [20-00-0186-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0186-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

26
8 Usability of the module
B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References
- Script of Lecture

- J. Nocedal, S.J. Wright: Numerical Optimization, Springer

- C.T. Kelley: Iterative Methods for Optimization, SIAM Frontiers in Applied Mathematics
- L.M. Rios, N.V. Sahinidis: Derivative-free optimization: a review of algorithms and comparison of software
implementations, Journal of Global Optimization (2013) 56:1247-1293
- A.E. Bryson, Y.-C. Ho: Applied Optimal Control: Optimization, Estimation and Control, CRC Press
- J.T. Betts: Practical Methods for Optimal Control and Estimation Using Nonlinear Programming, SIAM
Advances in Design and Control
10 Comment

27
Module name
Optimization Algorithms
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0667 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Karsten Weihe
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0667-iv Optimization Algorithms 0 Integrated 4
course
2 Teaching content
Algorithmic standard approaches to complex discrete optimization problems; for example, evolution strategies,
dynamic programming, branch-and-bound, etc.
3 Learning objectives
In this course students acquire systematic knowledge of generic algorithmic approaches in discrete optimization
and the abitiliy to tackle complex discrete optimization problems algorithmically.
4 Prerequisite for participation
Funktionale und objektorientierte Programmierkonzepte, Algorithmen und Datenstrukturen or similar.
5 Form of examination
Course related exam:
• [20-00-0667-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0667-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Will be given in lecture.
10 Comment

28
Module name
Deep Generative Models
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1035 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr.-Ing. Michael Gösele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1035-iv Deep Generative Models 0 Integrated 4
course
2 Teaching content
Generative Models, Implicit and Explicit Models, Maximum Likelihood, Variational AutoEncoders, Generative
Adversarial networks, Numerical Optimization for Generative models, Applications in medical Imaging
3 Learning objectives
After students have attended the module, they can
- Explain the structure and operation of Deep Generative Models (DGM)
- Critically scrutinize scientific publications on the topic of DGMs and thus assess them professionally
- independently construct / implement basic DTMs in a high-level programming language designed for this
purpose
- Transfer the implementation and application of DTMs to different applications
4 Prerequisite for participation
- Python Programming
- Linear Algebra
- Image Processing/Computer Vision I
- Statistical Machine Learning
5 Form of examination
Course related exam:
• [20-00-1035-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1035-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B,Sc, Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References
No textbooks as such. Online materials will be made available during the course.
10 Comment

29
1.1.1.3 AI Systems

Module name
Advanced Data Management Systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1039 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1039-iv Advanced Data Management Systems 0 Integrated 4
course
2 Teaching content
This is an advanced course about the design of modern data management systems which has a heavy emphasis
on system design and internals. Sample topics include modern hardware for data management, main memory
optimisations, parallel and approximate query processing, etc.

The course expects the reading of research papers (SIGMOD, VLDB, etc.) for each class. Program-
ming projects will implement concepts discussed in selected papers. The final grade will be based on the
results of the programming projects. There will be no final exam.
3 Learning objectives
Upon successful completion of this course, the student should be able to:
- Understand state-of-the-art techniques for modern data management systems
- Discuss design decision of modern data management systems with emphasis on constructive improvements
- Implement advanced data management techniques and provide experimental evidence for design decisions
4 Prerequisite for participation
Solid Programming skills in C and C++
Scalable Data Management (20-00-1017-iv)
Information Management (20-00-0015-iv)
5 Form of examination
Course related exam:
• [20-00-1039-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1039-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

30
Module name
Analysis of Hybrid Systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1087 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr.-Ing. Heiko Mantel
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1087-vl Analyse Hybrider Systeme 0 Lecture 2
2 Teaching content
• Hybrid automata and important subclasses
• Reachability analysis of linear hybrid automata with flowpipes
• Differential dynamic logic
• Validity calculus for differential dynamic logic
• Modeling Principles of hybrid automata and differential dynamic logic
3 Learning objectives
Upon successful completion of the module, students will possess the following skills:
• Modeling Cyber-Physical Systems as hybrid automata and hybrid programs
• Specifying reachability properties and invariants of such models
• Understanding the difference between explorative and deductive verification
• Understanding basic verification algorithms for hybrid systems
• Awareness of typical modeling patterns and errors
4 Prerequisite for participation
Recommended: Basic knowledge of first-order logic and program verification (similar to the bachelor-level
courses “Aussagenlogik und Prädikatenlogik” and “Formale Methoden im Softwareentwurf ”)
Basic knowledge of ODEs (“Mathematik 3 für Informatiker” or similar)
5 Form of examination
Course related exam:
• [20-00-1087-vl] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1087-vl] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

31
Module name
Automated Theorem Proving
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0660 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Reiner Hähnle
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0660-iv Automated Theorem Proving 0 Integrated 4
course
2 Teaching content
- Theoretical foundations of calculi for automated theorem proving in first-order logic
- Correctness and completeness proofs
- Algorithms and datastructures used in first-order logic theorem provers
- Comparison of different approaches to first-order theorem proving
- Foundations of modern SAT and SMT solvers
3 Learning objectives
Successful participation in this course puts the students in a position where they can understand in detail how
various state-of-art automated theorem proving methods work, they are able to judge their pros and cons, and
they can apply them practically.
4 Prerequisite for participation
Highly recommeded is participation of lecture "Aussagen- und Prädiketenlogik" or similar moduls. Basic
knowledge of propositional logics and first-order logics
5 Form of examination
Course related exam:
• [20-00-0660-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0660-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Robinson, Voronkov: Handbook of Automated Reasoning, 2 vols., North-Holland
10 Comment

32
33
Module name
Concepts and Technologies for Distributed Systems and Big Data Processing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0951 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Dr.-Ing. Michael Eichberg
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0951-iv Concepts and Technologies for Dis- 0 Integrated 2
tributed Systems and Big Data Processing course
2 Teaching content
The course provides an overview of recent advances in distributed
systems for Big Data processing. The course starts presenting
computational models for high throughput batch processing like
MapReduce. Next, we will introduce software engineering techniques for
distributed systems such as REST and component-based architectures. We will then cover low latency real time
stream processing and complex
event processing. Finally, we will present advanced topics in
distributed data-intensive systems, such as geodistribution and
security.

The course focuses both on the fundamental concepts as well

as on the concrete technologies and applications of the aforementioned
techniques to real-world case studies.
3 Learning objectives
- The students are familiar with basic concepts and technologies on
distributed systems and big data and are able to implement basic cloud
based/distributed applications.

- The students are familiar with the fundamental computational models

behind recent advances in distributed systems, such as models for
batch processing of massive data amounts, stream processing and
complex event processing.

- The students are familiar with selected advanced topics on big data,
including security and geolocalization.

- The students know about real-world case studies that apply the
concepts and the technologies presented during the course.
4 Prerequisite for participation
This course is targeted at master students.
5 Form of examination
Course related exam:
• [20-00-0951-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading

34
 Course related exam:
• [20-00-0951-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

35
Module name
Scalable Data Management Systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1017 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1017-iv Scalable Data Management Systems 0 Integrated 4
course
2 Teaching content
This course introduces the fundamental concepts and computational paradigms of scalable data management
systems. The focus of this course is on the systems-oriented aspects and internals of such systems for storing,
updating, querying, and analyzing large datasets.

Topics include:

Database Architectures
Parallel and Distributed Databases
Data Warehousing
MapReduce and Hadoop
Spark and its Ecosystem
Optional: NoSQL Databases, Stream Processing, Graph Databases, Scalable Machine Learning
3 Learning objectives
After the course the student will have a good overview of the different concepts, algorithms, and systems aspects
of scalable data management. The main goal is that the students will know how to design and implement such
systems including hands-on experience with state-of-the-art systems such as Spark.
4 Prerequisite for participation
Programming in C++ and Java
Informationsmanagement (20-00-0015-iv)

Optional:
Foundations of Distributed Systems (20-00-0998-iv)
5 Form of examination
Course related exam:
• [20-00-1017-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1017-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

36
10 Comment

37
1.1.1.4 AI Domains and Applications

Module name
3D Scanning & Motion Capture
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1180 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Ph. D. Jan Peters
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1180-iv 3D Scanning & Motion Capture 0 Integrated 4
course
2 Teaching content
The lecture and exercises will cover 3D reconstruction from various input modalities (Webcams, RGB-D cameras
(Kinect, Realsense, . . . ). It will start with basic concepts of what is 3D, the different representations, how to
capture 3D and how the devices and sensors function. Based on this introduction, rigid and non-rigid tracking
and reconstruction will be discussed. Specialized face and body tracking methods will be covered and the
applications of the 3D reconstruction and tracking will be shown. In addition to the 3D surface reconstruction,
techniques for appearance modelling and material estimation will be shown.
• Basic concepts of geometry (Meshes, Point Clouds, Pixels & Voxels)
• RGB and Depth Cameras (Calibration, active/passive stereo, Time of Flight (ToF), Structured Light, Laser
Scanner, Lidar)
• Surface Representations (Polygonal meshes, parametric surfaces, implicit surfaces (Radial basis functions,
signed distance functions, indicator function), Marching cubes)
• Overview of reconstruction methods (Structure from Motion (SfM), Multi-view Stereo (MVS), SLAM,
Bundle Adjustment)
• Rigid Surface Tracking & Reconstruction (Pose alignment, ICP, online surface reconstruction pipeline
(KinectFusion), scalable surface representations (VoxelHashing, OctTrees), loop closures and global
optimization)
• Non-rigid Surface Tracking & Reconstruction (Surface deformation for modeling, Regularizers:
ARAP, ED, etc., Non-rigid surface fitting: e.g., non-rigid ICP. Non-rigid reconstruction: DynamicFu-
sion/VolumeDeform/KillingFusion)
• Face Tracking & Reconstruction (Keypoint detection & tracking, Parametric / Statistical Models ->
BlendShapes)
• Body Tracking & Reconstruction (Skeleton Tracking and Inverse Kinematics, Marker-based motion capture)
• Material capture (Lightstage, BRDF estimation)
• Outlook DeepLearning-based tracking

3 Learning objectives
After successful completion of the module students have a basic understanding of 3D capturing devices and
underlying principles (active vs. passive stereo, ToF etc.), modelling of geometry and conversion between
different representations, principles of static reconstruction (fusion, ICP) and non-rigid reconstruction using
deformation priors. They will hab a basic understanding of specialized class-specific tracking (face, body, hands)
and their applications.
4 Prerequisite for participation

38
 Recommended:
- "Algorithms and Data Structures"
- "Graphical Data Processing I"
- Knowledge of fundamentals from higher mathematics
- Knowledge about basics of Deep Learning
- Programming knowledge in C / C++
5 Form of examination
Course related exam:
• [20-00-1180-iv] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1180-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

39
Module name
Ambient Intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0390 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0390-iv Ambient Intelligence 0 Integrated 4
course
2 Teaching content
The course will provide an overview of a new vision for Human-Computer-Interaction (HCI) in which people are
surrounded by intelligent and intuitive interfaces embedded in the everyday objects around them. In specific
the course addresses the emergence of Ambient Mobility and the ubiquitous, pervasive information access,
retrieval and display on mobile devices. It will focus on understanding enabling technologies and studying
applications and experiments, and, to lesser extent, it will adress the sociocultural impact. Additional topics of
the lecture include system architectures for distributed systems, context awareness and management, user
models and their implications, sensing and interaction in smart environments. The lecture discusses recent
topics and research projects in the domain of Ambient Intelligence.
3 Learning objectives
After successfully attending the lecture, the students will be able to describe technology trends and research
results in the domain of Ambient Intelligence. The most important concepts to create smart environments
- intelligent networks and objects, technologies for mobile, augmented reality, ubiquitous and pervasive
information spaces, nomadic communications, real-time communication and related middle ware, embedded
systems, sensor networks and wearable computing - can be discussed and classified. After completing the
practical part, students will be able to plan and realize the different project phases required to develop an
Ambient-Intelligence solution.
4 Prerequisite for participation
Master-Students
Participation in lecture “Visual Computing“ and „Multimodale Interaktion mit intelligenten Umgebungen“
5 Form of examination
Course related exam:
• [20-00-0390-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0390-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

40
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Will be given according to actual topics.
10 Comment

41
Module name
Bioinformatics
Module nr. Credit points Workload Self-study Module duration Module cycle
10-30-0036 4 CP 120 h 60 h 1 Term Every 2. Semester
Language Module owner
German
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
10-01-0036-vl Bio Informatics-Lecture 0 Lecture 2
10-01-0036-se Bio Informatics-Exercise 0 Practice 2
2 Teaching content

3 Learning objectives

4 Prerequisite for participation

5 Form of examination
Module exam:
• Module exam (Technical examination, Oral examination, Default RS)

6 Prerequisite for the award of credit points

Passing the final module examination
7 Grading
Module exam:
• Module exam (Technical examination, Oral examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

42
Module name
Capturing Reality
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0489 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0489-iv Capturing Reality 0 Integrated 4
course
2 Teaching content
This course covers a broad range of techniques to capture and model our world with a focus on application in
computer graphics and computer vision. This includes:
- basic tools and calibration techniques required in capturing applications
- capturing and modeling techniques for various object properties (such as geometry and reflectance)
- basic set of relevant mathematical modeling and optimization techniques
- implementation and practical application of several techniques
3 Learning objectives
After successful completion of the course, students are able to analyze digitization and modeling problems for
objects and scenes in computer graphics and computer vision as well as the underlying techniques. They are
able to develop new setups, perform experiments and evaluate the results.
4 Prerequisite for participation
Recommended:
Participation in lecture Graphische Datenverarbeitung I or Computer Vision I
Basic knowledge in C/C++
5 Form of examination
Course related exam:
• [20-00-0489-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0489-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

43
 Noriko Kurachi: The Magic of Computer Graphics. A K Peters/CRC Press
Richard Szeliski: Algorithms and Applications, Springer
Marcus Magnor, Oliver Grau, Olga Sorkine-Hornung, Christian Theobalt: Digital Representations of the Real
World: How to Capture, Model, and Render Visual Reality
Wolfgang Förstner, Bernhard P. Wrobel: Photogrammetric Computer Vision - Geometry, Orientation and
Reconstruction
10 Comment

44
Module name
Computer Vision I
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0157 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0157-iv Computer Vision 0 Integrated 4
course
2 Teaching content
- Basics of image formation
- Linear and (simple) nonlinear image filtering
- Foundations of multi-view geometry
- Camera calibration and pose estimation
- Foundations of 3D reconstruction
- Foundations of motion estimation from video
- Template and subspace methods for object recognition
- Object classification with bag of words
- Object detection
- Basics of image segmentation
3 Learning objectives
After successfully attending the course, students are familiar with the basics of computer vision. They understand
fundamental techniques for the analysis of images and videos, can name their assumptions and mathematical
formulations, as well as describe the resulting algorithms. They are able to implement these techniques in
order to solve basic image analysis tasks on realistic imagery.
4 Prerequisite for participation
Particiation of lecture Visual Computing is recommended.
5 Form of examination
Course related exam:
• [20-00-0157-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0157-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

45
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References
Literature recommendations will be updated regularly, an example might be:
- R. Szeliski, ""Computer Vision: Algorithms and Applications"", Springer 2011
- D. Forsyth, J. Ponce, ""Computer Vision – A Modern Approach"", Prentice Hall, 2002
10 Comment

46
Module name
Computer Vision II
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0401 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0401-iv Computer Vision II 0 Integrated 4
course
2 Teaching content
- Computer vision as (probabilistic) inference
- Robust estimation and modeling
- Foundations of Bayesian networks and Markov random fields
- Basic inference and learning methods in computer vision
- Image restoration
- Stereo
- Optical flow
- Bayesian tracking of (articulated) objects
- Semantic segmentation
- Current research topics
3 Learning objectives
After successfully attending the course, students have developed a more in-depth understanding of computer
vision. They formulate image and video analysis tasks as inference problems, taking challenges of real applica-
tions into account, e.g. regarding robustness. They solve the inference problem using discrete or continuous
inference algorithms, and apply these to realistic imagery. They quantitatively evaluate the application specific
results.
4 Prerequisite for participation
Participation of lecture Visual Computing and Computer Vision I is recommended.
5 Form of examination
Course related exam:
• [20-00-0401-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0401-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

47
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Literature recommendations will be updated regularly, an example might be:
- S. Prince, “Computer Vision: Models, Learning, and Inference”, Cambridge University Press, 2012
- R. Szeliski, ""Computer Vision: Algorithms and Applications"", Springer 2011
10 Comment

48
Module name
Ethics in Natural Language Processing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1061 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1061-iv Ethics in Natural Language Processing 0 Integrated 4
course
2 Teaching content
Machine Learning and Natural Language technologies are integrated in more and more aspects of our life.
Therefore, the decisions we make about our methods and data are closely tied up with their impact on our
world and society. In this course, we present real-world, state-of-the-art applications of natural language
processing and their associated ethical questions and consequences. We also discuss philosophical foundations
of ethics in research.

Core topics of this course:

- Philosophical foundations: what is ethics, history, medical and psychological experiments, ethical
decision making.
- Misrepresentation and bias: algorithms to identify biases in models and data and adversarial approaches to
debiasing.
- Privacy: algorithms for demographic inference, personality profiling, and anonymization of demographic and
personal traits.
- Civility in communication: techniques to monitor trolling, hate speech, abusive language, cyberbullying, toxic
comments.
- Democracy and the language of manipulation: approaches to identify propaganda and manipulation in news,
to identify fake news, political framing.
- NLP for Social Good: Low-resource NLP, applications for disaster response and monitoring diseases, medical
applications, psychological counseling, interfaces for accessibility.
3 Learning objectives
After completion of the lecture, the students are able to
- explain philosophical and practical aspects of ethics
- show the limits and limitations of machine learning models
- Use techniques to identify and control bias and unfairness in models and data
- Demonstrate and quantify the impact of influencing opinions in data processing and news
- Identify hate speech and online abuse and develop countermeasures
4 Prerequisite for participation
Basic knowledge of algorithms, data structure and programming
5 Form of examination
Course related exam:
• [20-00-1061-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading

49
 Course related exam:
• [20-00-1061-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

50
Module name
Foundations of Language Technology
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0546 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0546-iv Foundations of Language Technology 0 Integrated 4
course
2 Teaching content
This lecture provides an introduction into the fundamental perspectives, problems, methods, and techniques of
text technology and natural language processing using the example of the Python programming language.

Key topics:

- Natural language processing (NLP)

- Tokenization
- Segmentation
- Part-of-speech tagging
- Corpora
- Statistical analysis
- Machine Learning
- Categorization and classification
- Information extraction
- Introduction to Python
- Data structures
- Structured programming
- Working with files
- Usage of libraries
- NLTK library

The course is based on the Python programming language together with an open-source library called the
Natural Language Toolkit (NLTK). NLTK allows explorative and problem-solving learning of theoretical
concepts without the requirement of extensive programming knowledge.
3 Learning objectives
After attending this course, students are in a position to
- define the fundamental terminology of the language technology field,
- specify and explain the central questions and challenges of this field,
- explicate and implement simple Python programs,
- transfer the learned techniques and methods to practical application scenarios of text understanding, as well
as
- critically assess their merits and limitations.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-0546-iv] (Technical examination, Oral/written examination, Default RS)

51
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0546-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Steven Bird, Ewan Klein, Edward Loper: Natural Language Processing with Python, O'Reilly, 2009. ISBN:
978-0596516499. http://www.nltk.org/book/
10 Comment

52
Module name
Foundations of Robotics
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0735 10 CP 300 h 210 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0735-iv Foundations of Robotics 0 Integrated 6
course
2 Teaching content
This course covers spatial representations and transformations, manipulator kinematics, vehicle kinematics,
velocity kinematics, Jacobian matrix, robot dynamcis, robot sensors and actuators, robot control, path
planning, localization and navigation of mobile robots, robot autonomy and robot development.

Theoretical and practical assignments as well as programming tasks serve for deepening of the understanding
of the course topics.
3 Learning objectives
After successful participation, students possess the basic technical knowledge and methodological skills necessary
for fundamental investigations and engineering developments in robotics in the fields of modeling, kinematics,
dynamics, control, path planning, navigation, perception and autonomy of robots.
4 Prerequisite for participation
Recommended: basic mathematical knowledge and skills in linear algebra, multi-variable analysis and funda-
mentals of ordinary differential equations
5 Form of examination
Course related exam:
• [20-00-0735-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0735-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

53
10 Comment

54
Module name
Intelligent Robotic Manipulation: Advanced topics in Robot Perception, Planning and Control
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1181 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1181-iv Intelligent Robotic Manipulation: Ad- 0 Integrated 4
vanced topics in Robot Perception, Plan- course
ning and Control
2 Teaching content
This course introduces fundamental algorithmic approaches for creating robot systems that can autonomously
manipulate physical objects in unstructured environments such as homes. We will cover basic principles for
endowing autonomous robots with planning, perception, and decision-making capabilities, i.e., topics include
perception (including approaches based on deep learning and approaches based on 3D geometry), planning
(robot kinematics and trajectory generation, collision-free motion planning, task-and-motion planning, and
planning under uncertainty), as well as dynamics and control for adaptive and reactive manipulation.

Tentative list of topics:

• Topology in robotics and rigid body motions
• Refresher on forward, inverse kinematics and dynamics
• Differential kinematics and optimization
• Geometric perception and object pose detection
• Object pose estimation and tracking and multi-sensor fusion
• Grasp generation and grasp evaluation
• Trajectory Optimization
• Search and Sampling-based motion planning
• Force control
• Visuomotor policies and intuitive physics
• Task and motion planning and belief-space planning
Practical exercises will guide understanding fundamental mathematical and algorithmic principles for enabling
robotic manipulators to perceive their environment, estimate the current state of the robot itself and the robots
or humans in their surroundings, and create a strategy for executing various tasks that involve autonomously
manipulating objects in cluttered scenes.
3 Learning objectives
After completeing the module students will have learned the theoretical, algorithmic, and implementation
aspects of main techniques for autonomous and intelligent robotic manipulation, in particular modeling &
controls, motion planning, perception, estimation, state machines, and decision making.

With this class, the student will:

• have gained a fundamental knowledge of the “intelligence and autonomy stack” behind autonomous
robots in general.
• be able to apply such knowledge in applications and research work.
• devise novel methods and algorithms for intelligent robotic manipulation.

4 Prerequisite for participation

55
 Recommended:
The students should have a fundamental knowledge of robotics and linear algebra. Furthermore, Fundamentals
of Robotics (20-00-0735-iv Grundlagen der Robotik) is recommended. Experience in Robot Learning
(20-00-0629-vl Lernende Roboter) is also a plus.

Combining the course with the seminar and project lab will equip the students with a greater under-
standing and in-depth knowledge of the necessary components and principles to enable robotic autonomous
manipulation.
5 Form of examination
Course related exam:
• [20-00-1181-iv] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass Exam (100%).
7 Grading
Course related exam:
• [20-00-1181-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

56
Module name
Learning and Educational Technologies
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0773 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Eberhard Mühlhäuser
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0773-iv Learning and Educational Technologies 0 Integrated 4
course
2 Teaching content
Digital applications and the Internet are changing the way we learn. If digital teaching and learning applications
are designed appropriately, they offer a wide range of possibilities. The module aims to impart basic knowledge
about the most important aspects of system design and about technologies needed for modern, web-based and
mobile learning applications. Important theoretical foundations for the design of learning applications are
learning theories. Therefore, learning theories are briefly discussed in the context of this module. The focus
of the module is on adaptive learning applications. Different methods for the realization of adaptive learning
applications will be presented. Frequently, Natural Language Processing and Artificial Intelligence methods
are used for this purpose. In this context, current research work is considered. The module also focuses on
the design of learning applications for individual and cooperative learning in various fields of application (e.g.
school, university, vocational education and lifelong learning). Examples from current research projects as well
as teaching/learning practice are presented. In addition, methods for the evaluation of learning applications
are considered.
3 Learning objectives
After completion of the module, students will be able to analyze and design applications for knowledge
acquisition and learning based on different design patterns and technologies. They will be able to decide on
information representation (data level), design of functionalities (application level), and selection/configuration
of algorithms to support platform users concerning challenges in the learning process. Students are capable
to consider techniques of adaptation to learners needs and will know appropriate evaluation methods to
measure the qualities and effects of learning applications and the algorithms and methods used in the learning
applications.
4 Prerequisite for participation
Basic knowledge of Machine Learning and Natural Language Processing is desirable but not a prerequisite. For
students who do not meet these requirements, we offer short learning modules that allow an understanding of
the application-specific mechanisms.
5 Form of examination
Course related exam:
• [20-00-0773-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0773-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

57
 B.Sc. Informatik
M.Sc. Informatik
Kann in anderen Studiengängen verwendet werden.
9 References

10 Comment

58
Module name
Human and Identity centric Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1118 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Arjan Kuijper
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1118-iv Human and Identity centric Machine 0 Integrated 4
Learning course
2 Teaching content
Background and concepts of human-centric Machine Learning: the goal of identity and human-centric machine
learning. The differences between identity learning and other
mainstream classification. Representation extraction for subject-related data: feature extraction methodology
for identity related applications. Hand crafted and Deeply learned features background and
basics.

Deep learning strategies for identity representations: learning identities representations with deep
learning. Learning strategies and learning losses. Network architectures and identityspecific components.

Knowledge transfer and distillation: transfer learning and identity-representation. Knowledge distil-
lation concepts and applications.

Efficient machine learning: the relation between resource limitations, Green-AI, and deep learning.
Methods to build efficient machine learning solutions.

Synthetic identity: the need of synthetic identity. Synthetic identity as adversarial. Generating syn-
thetic identity-controlled data under different restrictions.

Machine learning biases: analyses of demographic fairness and the roots of the fairness issues. ML-
based mitigation of demographic biases.

Learning privacy: analyzing unintentionally learned information. Learning strategies to the targeted
suppression of information at different representation levels.

Data utility: understanding the effect of data utility in the training process. Understanding sample
utility in operation. ML concepts and strategies of estimating sample utilities.

Sample-level attacks: overview on adversarial, sample manipulation, other attacks on human-centric

ML. Deep learning concepts, network blocks, and loss strategies, to detect and mitigate sample-level attacks.

Explainability: overview on the need for explainability in different decision-making processes. Differ-
ent strategies to provide explainability for decision made in different operations discussed in the previous
lectures.

Ethics in identity-centric ML: overview on ethics in AI and AI regulation. AI ethics for human data
processing and storage.
3 Learning objectives

59
 After successfully attending the module, students are familiar with machine learning concepts related to dealing
with human and identity related information. They understand fundamental techniques for the subject-specific
representation extraction, including related knowledge transfer and distillation concepts. Understanding
of demographic-related machine learning biases and function-creep privacy concerns, including their main
mitigation concepts. They understand the requirements and techniques to achieve embedded and efficient
human-centric machine learning. They are familiar with the effect of data utility in the training process and
the main concept to estimate the utility of subject-related data.
They will have first hand understanding of explainability methodologies of ML decision based on identity-related
data. The students will be introduced to AI ethics and AI regulation concepts related to human data processing
and storage. They are able to implement these techniques in order to solve basic identity and human-centric
machine learning tasks on realistic problems.
4 Prerequisite for participation
It is recommended having previously taken Visual Computing. Basics in mathematics and probability theory
are required.
5 Form of examination
Course related exam:
• [20-00-1118-iv] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1118-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

60
Module name
Model Predictive Control and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
18-fi-2040 4 CP 120 h 75 h 1 Term Winter term
Language Module owner
English Prof. Dr.-Ing. Rolf Findeisen
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
18-fi-2040-vl Model Predictive Control and Machine 0 Lecture 2
Learning
18-fi-2040-ue Model Predictive Control and Machine 0 Practice 1
Learning
2 Teaching content
Lecture:
Introduction and basics of optimal control, Linear Quadratic Regulator (LQR) in discrete and continuous time,
basics of model predictive control (cost functions, constraints, receding horizon), nominal model predictive
control for linear systems, robust and stochastic model predictive control, model predictive control of nonlinear
systems, combination of machine learning and model predictive control.

Group work:
In a group project, the students will apply the learned. The group project evolves a review of state of the art
for the selected task, the selection of suitable model predictive control approach, and the implementation using
python/Matlab. It includes a project report and is concluded by a project presentation.
3 Learning objectives
The students will understand the basics concepts of model predictive control. Furthermore, they are familiarized
with machine learning approaches that can support model predictive controllers and possibly enhance the
controller performance. This entails knowledge about theoretical questions such as stability in the nominal
case, as well as extensions to the case of uncertain and disturbed systems. The students are enabled to design
and implement model predictive controllers based on first principle/physical or data-based/machine learning
based models. This entails the setup and design of the control structure as well as the tuning and identification
of suitable parameters and cost functions of the controller.
4 Prerequisite for participation
Recommended: Basic concepts of control theory. Fundamentals of linear algebra, differential, and difference
equations. Knowledge in Python and/or Matlab.
5 Form of examination
Module exam:
• Module exam (Technical examination, Oral/written examination, Duration: 90 Min., Default RS)
The examination takes place in form of a written exam (duration: 90 minutes). If one can estimate that
less than 25 students register, the examination will be an oral examination (duration: 25 min.). The type of
examination will be announced in the beginning of the lecture.
6 Prerequisite for the award of credit points
Passing the final module examination
7 Grading
Module exam:
• Module exam (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

61
9 References

• J. Rawlings, D. Mayne, and M. Diehl. Model predictive control: theory, computation, and design. Nob
Hill Publishing.
• S. Rakovic, and W. Levine. Handbook of Model Predictive Control. Birkhäuser, 2018.

10 Comment

62
Module name
Natural Language Processing and the Web
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0433 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0433-iv Natural Language Processing and the Web 0 Integrated 4
course
2 Teaching content
The Web contains more than 10 billion indexable web pages, which can be retrieved via keyword search
queries. The lecture will present natural language processing (NLP) methods to automatically process large
amounts of unstructured text from the web and analyze the use of web data as a resource for other NLP tasks.

Key topics:

- Processing unstructured web content

- NLP basics: tokenization, part-of-speech tagging, stemming, lemmatization, chunking
- UIMA: principles and applications
- Web contents and their characteristics, incl. diverse genres such as personal web sites, news sites, blogs,
forums, wikis
- The web as a corpus - innovative use of the web as a very large, distributed, interlinked, growing, and
multilingual corpus
- NLP applications for the web
- Introduction to information retrieval
- Web information retrieval and natural language interfaces
- Web-based question answering
- Mining Web 2.0 sites such as Wikipedia, Wiktionary
- Quality assessment of web contents
- Multilingualism
- Internet of services: service retrieval
- Sentiment analysis and community mining
- Paraphrases, synonyms, semantic relatedness
3 Learning objectives
After attending this course, students are in a position to
- understand and differentiate between methods and approaches for processing unstructured text,
- reconstruct and explicate the principle of operation of web search engines,
- construct and analyze exemplary NLP applications for web data,
- analyze and evaluate the potential of using web contents to enhance NLP applications.
4 Prerequisite for participation
Basic knowledge in Algorithms and Data Structure
Programming in Java
5 Form of examination
Course related exam:
• [20-00-0433-iv] (Technical examination, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)

63
7 Grading
Course related exam:
• [20-00-0433-iv] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
- Kai-Uwe Carstensen, Christian Ebert, Cornelia Endriss, Susanne Jekat, Ralf Klabunde: Computerlinguistik und
Sprachtechnologie. Eine Einführung. 3. Auflage. Heidelberg: Spektrum, 2009. ISBN: 978-3-8274-20123-7.
- http://www.linguistics.rub.de/CLBuch/
- T. Götz, O. Suhre: Design and implementation of the UIMA Common Analysis System, IBM Systems Journal
43(3): 476-489, 2004.
- Adam Kilgarriff, Gregory Grefenstette: Introduction to the Special Issue on the Web as Corpus, Computational
Linguistics 29(3): 333-347, 2003.
- Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze: Introduction to Information Retrieval,
Cambridge: Cambridge University Press, 2008. ISBN: 978-0-521-86571-5. http://nlp.stanford.edu/IR-book/
10 Comment

64
Module name
Technology transfer and entrepreneurship with a focus on artificial intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1176 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1176-vl Technology transfer and entrepreneurship 0 Lecture 2
with a focus on artificial intelligence
2 Teaching content
The module is aimed at all PhD students and students of TU Darmstadt from the 2nd semester onwards,
especially those who are currently or in the future considering founding a start-up or spin-off. Parts of the
lecture will take place remotely. It is planned to include entrepreneurs from practice in this context.
In terms of content, this module deals with methods for goal-oriented idea generation and their critical reflection,
procedures for estimating the market and market potential, and the analysis of competitors. In addition, various
business models and growth strategies are discussed and their implications for monetization and scalability
are taught. Furthermore, the fundamentals of sales and marketing are taught, as well as the procurement of
personnel, incentives and employee participation, acquisition of venture capital, corporate culture, operations
and management, preparation of business plans, and legal principles and liability issues.
3 Learning objectives
Upon successful completion of the module, students will have learned the fundamentals of transferring scientific
results to practical applications and will be able to apply the content taught.
4 Prerequisite for participation
No previous experience is required.
5 Form of examination
Course related exam:
• [20-00-1176-vl] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.
Written exam (duration 60 or 90 or 120 minutes), oral exam (duration 15 or 30 minutes), homework (optional:
including tests).
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1176-vl] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

65
1.1.2 Study-related Achievements

1.1.2.1 Seminars

Module name
Recent Topics in the Development and Application of Modern Robotic Systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0148 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0148-se Recent Topics in the Development and 0 Seminar 2
Application of Modern Robotic Systems
2 Teaching content
- guided independent work on a concrete task from development and application of modern robotic systems
- becoming acquainted with the relevant state of research and technology
- development of a solution approach and its presentation and discussion in a talk and in a final report
3 Learning objectives
Through successful participation students acquire deepened knowledge in selected areas, subsystems and
methods of modern robotic systems and train presentation and documentation skills.
4 Prerequisite for participation
Basic knowledge in Robotics as given in lecture “Grundlagen der Robotik”.
5 Form of examination
Course related exam:
• [20-00-0148-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0148-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References
Will be given in lecture.
10 Comment

66
67
Module name
Deep Learning and Digital Humanities
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1080 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1080-se Deep Learning and Digital Humanities 0 Seminar 2
2 Teaching content
Our focus will be on humanities applications such as Poetry Generation and Analysis, Metaphor Identification,
analysis of emotions, and others, and how these can be solved with the help of Deep Learning techniques.
Students will read papers and present them during the seminar.
3 Learning objectives
After this seminar, students will be able to:
* understand problems in the field of digital humanities
* understand how Deep Learning can used to solve these problems
* implement crowd-sourcing techniques for annotation
4 Prerequisite for participation
Lecture Deep Learning is helpful, but not required.
5 Form of examination
Course related exam:
• [20-00-1080-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1080-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

68
Module name
Extended Seminar - Systems and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1057 4 CP 120 h 75 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1057-se Extended Seminar - Systems and Machine 0 Seminar 3
Learning
2 Teaching content
This seminar serves the purpose of discussing new research papers in the intersection of hardware/software-
systems and machine learning. The seminar aims to elicit new connections amongst these fields and discusses
important topics regarding systems questions machine learning including topics such as hardware accelerators
for ML, distributed scalable ML systems, novel programming paradigms for ML, Automated ML approaches, as
well as using ML for systems.

Every participant will present one research paper, which will be subsequently discussed by all partici-
pants. In addition, summary papers will be written in groups and submitted to a peer review process. The
papers will typically be recent publications in relevant research venues and journals.

The seminar will be offered as a block seminar. Further information can be found at: http://binnig.name
3 Learning objectives
After this seminar, the students should be able to
- understand a new research contribution in the areas of the seminar
- prepare a written report and present the results of such a paper in front of an audience
- participate in a discussion in the areas of the seminar
- to peer-review the results of other students
4 Prerequisite for participation
Basic knowledge in Machine Learning, Data Management, and Hardware-/Software-Systems.
5 Form of examination
Course related exam:
• [20-00-1057-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1057-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B. Sc Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

69
70
Module name
Extended Seminar - AI for Data Management
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1182 4 CP 120 h 75 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1182-se Extended Seminar - AI for Data Manage- 0 Seminar 3
ment
2 Teaching content
Database management systems (DBMS) in the cloud are the backbone for managing large volumes of data
efficiently and thus play a central role in business and science today. For providing high performance, many of
the most complex DBMS components such as query optimizers or schedulers involve solving non-trivial problems.

To tackle such problems, very recent work has outlined a new direction of so-called learned DBMS
components where AI-based methods are used to replace and enhance core DBMS components which has
shown to provide significant performance benefits. This route is in particular interesting since Cloud vendors
such as Google, Amazon, and Microsoft are already applying these techniques to optimize the performance
their cloud data systems.

Furthermore, AI has also been used for improving many other data management related tasks such
as data engineering tasks (e.g., error detection and correction in databases or data transformation and data
augmentation) which typically cause high manual overhead and can be automated by the use of AI. Finally, AI
has also been used for extending databases by better data access interfaces (e.g., natural languague querying
and chatbots for data) or by supporting data beyond structured tabular data (i.e., text and images).

This seminar serves the purpose to understand the basic concepts of how AI can be used for data
management. In the first part of the seminar, participants will learn the basics of AI for data management along
with implementing a case study themselves. In the second part, every participant will select and present a
recent research paper. The papers will typically be recent publications in relevant research venues and journals
such as SIGMOD, VLDB or ICML, NeurIPS.

The seminar kick-off will typically be in the first two weeks of the semester where we discuss the
organization of the seminar. Further information can be found at: http://tuda.systems
3 Learning objectives
After successfully completeing this module Students are able to
• apply basic concepts of AI to data management
• read and understand a new research contribution in the areas of the seminar
• prepare and present the results of such a paper in front of an audience
• participate in a discussion in the areas of the seminar
• to peer-review the results of other students

4 Prerequisite for participation

Recommended:
Basic knowledge in Machine Learning and programming in Python and ideally C++. Advanced knowledge in
Data Management, and Database-Systems by attending courses such as SDMS or ADMS.
5 Form of examination

71
 Course related exam:
• [20-00-1182-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:
Colloquium (optional: including presentation), Term Paper.
6 Prerequisite for the award of credit points
Pass Exam (100%).
7 Grading
Course related exam:
• [20-00-1182-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

72
Module name
Advanced Topics in Computer Vision and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0645 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr.-Ing. Michael Gösele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0645-se Advanced Topics in Computer Vision and 0 Seminar 2
Machine Learning
2 Teaching content
- Basics of scientific presentations and reviewing
- Independent familiarization with current publications in computer vision or machine learning (in English)
- Further research on background literature, with help from a mentor
- Preparation of a two-part slide presentation (problem statement and proposed solution) of one publication,
with feedback from mentor
- Writing a scientific “mock” review of another publication, with aid from mentor
- Giving the presentation in front of a mixed audience
- Guiding the interactive discussion after both presentation parts
- Active participation in discussions, including feedback to presenters
3 Learning objectives
After successfully completing the seminar, students are able to use recent scientific publications to become
acquainted with current topics in computer vision and/or machine learning in an independent fashion. They
can recognize the key contributions of the publications and are able to present them to a heterogeneous
audience, taking into account good practices of scientific presentation. They can direct a scientific discussion
following the presentation. Moreover, they are able to author a scientific review following common standards
of the scientific review process.
4 Prerequisite for participation
Teilnehmer sollten Grundkenntnisse in Computer Vision, sowie idealerweise maschinellem Lernen besitzen
(z.B. durch Besuch von Computer Vision I, Maschinelles Lernen: Statistische Verfahren I).
5 Form of examination
Course related exam:
• [20-00-0645-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0645-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

73
 B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Actual publications, mostly last year.
10 Comment

74
Module name
Humanoid Robotics
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1125 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1125-se Humanoid Robotics 0 Seminar 2
2 Teaching content
In this seminar, we will discuss different problems from the field of humanoid robotics, e.g. concerning
locomotion and whole-body control, planning, or perception. In the context of this seminar, students should
acquire the ability to independently work out an unknown text, write a scientific article and present its content
to an expert audience.
3 Learning objectives
Upon successful completion of the module, students will understand current research topics in humanoid
robotics and will be able to:
• Independently familiarize themselves with a topic area based on scientific publications, and
• present their findings verbally and in writing to a professional audience.

4 Prerequisite for participation

Concurrent or prior enrollment in the course "Foundations of Robotics" and/or "Robot Learning" is recommended.
5 Form of examination
Course related exam:
• [20-00-1125-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:
Colloquium (optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1125-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

75
Module name
Intelligent Robotic Manipulation
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1158 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1158-se Intelligent Robotic Manipulation: Part I 0 Seminar 2
2 Teaching content
This advanced seminar introduces fundamental algorithms for creating robot systems that can autonomously
perceive and manipulate objects in unstructured environments like homes, restaurants, supermarkets, etc. It
addresses the complex and timely challenge of understanding and developing intelligent robotic manipulation.
The seminar will discuss fundamental methods in perception (including approaches based on deep learning
and approaches based on 3D geometry), planning (robot kinematics and trajectory generation, collision-free
motion planning, task-and-motion planning, and planning under uncertainty), and dynamics and control
(mainly force control and its variants).

The seminar will contain a combination of introductory lectures and a reading group to discuss and
learn about advanced algorithmic approaches in robotics. After an introductory lecture on a new topic, small
groups of students will be assigned a research paper that is fundamental for each topic (depending on the class
size, there might be an alternating style). The students shall present the basic concept of the paper in class and
engage in discussion regarding the presented topics.
3 Learning objectives
After this advanced course, students will be able to understand the entire pipeline of robotic systems by
being immersed in the details of the fundamental paradigm of perception, planning, and action for robotic
manipulation. Students will then be familiar with various AI and control techniques that will enable them to
solve challenging intelligent robot manipulation problems. The goal is a holistic understanding of the science
of robotics for the field of manipulation.
4 Prerequisite for participation
Recommended:
The students should have fundamental knowledge in robotics, and linear algebra. Furthermore, Fundamentals
of Robotics (20-00-0735-iv Grundlagen der Robotik) is recommended.
5 Form of examination
Course related exam:
• [20-00-1158-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:

Colloquium (optional: including presentation).

6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1158-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

76
 B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

77
Module name
Intelligent Robotic Manipulation: Part II
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1168 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1168-se Intelligent Robotic Manipulation: Part II 0 Seminar 2
2 Teaching content
This advanced seminar introduces fundamental algorithms for creating robot systems that can autonomously
perceive and manipulate objects in unstructured environments like homes, restaurants, supermarkets, etc. It
addresses the complex and timely challenge of understanding and developing intelligent robotic manipulation.
The seminar will discuss fundamental methods in perception (including approaches based on deep learning
and approaches based on 3D geometry), planning (robot kinematics and trajectory generation, collision-free
motion planning, task-and-motion planning, and planning under uncertainty), and dynamics and control
(mainly force control and its variants).

The seminar will contain a combination of introductory lectures and a reading group to discuss and
learn about advanced algorithmic approaches in robotics. After an introductory lecture, small groups of
students (or individuals) will be assigned a research paper that is fundamental for each topic (depending on
the class size, there might be an alternating style). The students shall present the basic concept of the paper in
class and engage in discussion regarding the presented topics.

Possibly, a specific theme will be selected every semester, that will be announced by the lecturer in
Moodle.

List of topics (non-exhaustive):

• Refresher on kinematics and dynamics
• Pick-and-place pipeline
• Object pose estimation
• Grasp generation
• Robot force control (stiffness, impedance, admittance)
• Sampling-based motion planning
• Trajectory Optimization
• Task and Motion Planning
• Mobile Manipulation
• Human-Robot Interaction

3 Learning objectives
Students have the chance to gain knowledge in advanced topics in Robotics, AI and Learning. By presenting
high-end robotics research papers, the students learn how to communicate effectively scientific topics, and they
also will learn how to collaborate with their colleagues for preparing their presentation.
4 Prerequisite for participation
Recommended:
The students should have fundamental knowledge in robotics, and linear algebra. Furthermore, Fundamentals
of Robotics (20-00-0735-iv Grundlagen der Robotik) is recommended.
5 Form of examination

78
 Course related exam:
• [20-00-1168-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:
Colloquium (optional: including presentation), Term Paper.
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1168-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

79
Module name
Seminar Data Mining and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0102 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0102-se Seminar Data Mining and Machine Learn- 0 Seminar 2
ing
2 Teaching content
This seminar serves the purpose of discussing new research papers in the areas of data mining and machine
learning. Every participant will present one paper, which will be subsequently discussed by all participants.
Grades are based on the preparation and presentation of the paper, as well as the participation in the discussion,
in some cases also a written report.

The papers will typically recent publications in relevant journals such as “Data Mining and Knowl-
edge Discovery”, ""Machine Learning"", as well as ""Journal of Machine Learning Research"". Students may also
propose their own topics if they fit the theme of the seminar.

Please note current announcements to this course at http://www.ke.informatik.tu-darmstadt.de/lehre.

3 Learning objectives
After this seminar, students should be able to
- understand an unknown text in the area of machine learning
- work out a presentation for an audience proficient in this field
- make useful contributions in a scientific discussion in the area of machine learning
4 Prerequisite for participation
Basic knowledge in Machine Learning and Data Mining
5 Form of examination
Course related exam:
• [20-00-0102-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0102-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

80
9 References

10 Comment

81
Module name
Software Engineering for Artificial Intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1097 4 CP 120 h 75 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr.-Ing. Ermira Mezini
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1097-se Software Engineering for Artificial Intelli- 0 Seminar 3
gence
2 Teaching content
Data-driven artificial intelligence (AI) solutions are being adopted in many areas, including finance, medicine,
cognitive sciences, and biology. Such machine learning (ML) approaches require an accurate domain and
requirement analysis, proper software design and development, dedicated testing and debugging, as well
as specific techniques that ensure scalability and maintainability. While AI-enabled systems continue to
have a tremendous impact on many fields, developers and data scientists still follow methods (scripting,
informal/non-written specifications, trial-and-error testing) that do not conform to the state of the art of
engineering disciplines. In this context, it is of paramount importance to take advantage of the decades-long
developments of software engineering (SE) to systematize the development process of ML solutions.

In this course, each student will be assigned a topic regarding SE for AI. Based on provided resources and
personal extending research, each student prepares a presentation with following discussion. These will be
conducted in regular appointments. The students not presenting at a particular date, prepare via introductory
reading for the respective discussion. Grading will be based on the preparation of the assigned topic and its
presentation, as well as on the participation in all the discussions.

For more information and announcements, please consult the course webpage:
https://allprojects.github.io/SE4AI/
3 Learning objectives
After successful completion of the module students will have developed a deeper understanding of software
engineering for artificial intelligence. This includes the key topics requirements engineering, quality assurance,
development processes, and software architecture and design accounting for modularity, reusability, efficiency,
scalability, fairness and privacy.

The students learn the preparation and the presentation of scientific contents for an audience with
heterogeneous background knowledge. Moreover, students train efficient preparation of and active
participation in scientific discussions as well as their moderation.
4 Prerequisite for participation
Recommended: Basic knowledge of software engineering. Interest in artificial intelligence.
5 Form of examination
Course related exam:
• [20-00-1097-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:
Colloquium (optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading

82
 Course related exam:
• [20-00-1097-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

83
Module name
Symbolic Execution
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0702 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Reiner Hähnle
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0702-se Symbolic Execution 0 Seminar 2
2 Teaching content
Symbolic execution of programs is a fundamental analysis technique that forms the basis of test generation,
compiler optimization, verification, visualization, etc. In recent years, major progress was made. In the seminar
we review the most important classic as well as recent contributions to symbolic execution.
3 Learning objectives
Understanding the possibilities and the limitations of this fundamental program analysis technique.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-0702-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0702-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

84
Module name
Text Analytics
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0596 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0596-se Text Analytics 0 Seminar 2
2 Teaching content
The seminar introduces current topics in natural language processing. It provides a thorough introduction into
state-of-the-art technology in text analytics. The main focus of the seminar changes each semester.

Further information: https://www.ukp.tu-darmstadt.de/teaching/courses/regular-seminar/

3 Learning objectives
After attending this course, students are in a position to
- name and explain state-of-the-art research questions in the area of the seminar,
- understand, critically assess, and discuss scientific publications,
- independently comprehend and work out a research topic and
- present it to the group and react on questions and discussion threads.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-0596-se] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0596-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Will be given in seminar.
10 Comment

85
Module name
Computational Neuroscience
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1129 3 CP 90 h 60 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Michael Waidner
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1129-se Computational Neuroscience 0 Seminar 2
2 Teaching content
The subject of the seminar is the teaching of methods of model building for neuroscience. The functional
systems of the nervous system, including the brain, are among the most complex networks of interactions that
we can observe in nature. Moreover, biological neural networks are cognitive systems that are of particular
interest to computer science for this reason alone. The modeling of neural systems can be readily applied to
other non-biological systems (e.g., autonomous systems, transportation networks, logistics) and therefore serve
as a suitable use case to develop appropriate methodological skills. In the seminar, we will address observable
and simulatable nonlinear dynamics that are reciprocally coupled with each other in the nervous system on
different time scales, such as neuronal electrical activities and activity-dependent plastic processes, which
in turn change the activity flow on a much slower time scale. Using original publications, informatic and
mathematical methods are taught to model such processes and systems. The above-mentioned models will be
developed on different neuronal functional systems such as the visual or the hippocampal functional system for
memory formation.

Offered as a virtual interactive event (WebEx) with seminar presentations as live stream

Recommended reading:
- Dynamical Systems in Neuroscience, Eugene M. Izhikevich, The MIT Press, ISBN 978-0-262-51420-0.
- The Rewiring Brain, Arjen van Ooyen & Markus Butz-Ostendorf, Academic Press/Elsevier. ISBN:
978-0-12-803784-3
3 Learning objectives
After successful completion of the module the student are able to
• describe neuronal functional systems in their parts and their functional relations.
• to compare different functional systems.
• to know mathematical methods for non-linear dynamics.
• implement ordinary differential equations for neural simulations.
• know different neuron and brain simulators
• abstract over biological details and develop a formal neuronal model.
• to know different neuronal models and to evaluate them for the respective application.

4 Prerequisite for participation

Recommended:
- Mathematical methods from the bachelor program in computer science
- Algorithms and data structures
- Programming skills (programming language freely selectable)
- Basic understanding of biology is an advantage
5 Form of examination

86
 Course related exam:
• [20-00-1129-se] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible:
Colloquium (optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1129-se] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

87
1.1.2.2 Practical Lab in Teaching

Module name
Practical Lab in Teaching - Computational Engineering and Robotics
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0971 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0971-pl Practical Lab in Teaching - Computational 0 Internship 3
Engineering and Robotics teaching
2 Teaching content
- Elaboration of new exercises and programming assignments
- Concepts for exercise sheets
3 Learning objectives
After successfully completing the course, the students are familiar with the preparation of teaching contents as
excercises and programming assignments.
4 Prerequisite for participation
Prerequisite: Successful participation in "Introduction to Computational Engineering (and Robotics)"
Recommended: successful participation in "Foundations of Robotics"
5 Form of examination
Course related exam:
• [20-00-0971-pl] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0971-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

88
Module name
Data Management - Teaching Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1040 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1040-pl Data Management - Teaching Lab 0 Internship 3
teaching
2 Teaching content
Creation of lab exercises and teaching material
3 Learning objectives
Experience in the supervision of students on the topic of data management, especially with regard to using the
newly created material.
4 Prerequisite for participation
Information Management (20-00-0015-iv)
5 Form of examination
Course related exam:
• [20-00-1040-pl] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1040-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
9 References

10 Comment

89
Module name
Teaching Lab - Deep Learning for Natural Language Processing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1044 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1044-pl Teaching Lab - Deep Learning for Natural 0 Internship 3
Language Processing teaching
2 Teaching content
Organization of a shared tasks. In a shared task, the students are challenged to solve a current research problem.
They will use methods they learned in the lecture to solve a certain problem as good as possible. The different
solutions can be evaluated quantitatively to identify the best solution to the task. Your task is to select and
prepare an appropriate dataset for the task and to give an introduction to the task. During the shared task, you
are responsible to answer questions from the students and provide help if needed. After the submission, your
task is to evaluate the submitted systems quantitatively and qualitatively. Besides the shared task, you support
the weekly exercises, e.g., by answering student questions or by helping to grade the home exercises.
3 Learning objectives
The students work on problems that have both technical and didactic aspects and are involved in the imple-
mentation of the results they have developed.
4 Prerequisite for participation
Deep Learning for Natural Language Processing
5 Form of examination
Course related exam:
• [20-00-1044-pl] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1044-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

90
Module name
Practical Lab in Teaching - Introduction to Artificial Intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1132 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1132-pl Practical Lab in Teaching - Introduction 0 Internship 3
to Artificial Intelligence teaching
2 Teaching content
This course deals with the teaching content of artificial intelligence, which is to be prepared didactically and
made more comprehensible through accompanying practical exercises.

This includes, among other things:

• Designing and creating practical forms of exercises
• Offering office hours
• Supervising students
• Correcting exercise submissions
• Supporting the organization and realization of the exercises
• Making suggestions to improve the quality of teaching

3 Learning objectives
After successfully completing the modulee, students will be able to:
• Design and create practical exercises
• Prepare teaching content from the lecture for home and classroom exercises
• Support student groups didactically
• Critically question existing teaching materials and making suggestions for improvement
• Apply methods to evaluate the teaching success of the lecture content

4 Prerequisite for participation

Recommended: Successful completion of the course Introduction to Artificial Intelligence or equivalent knowl-
edge.
5 Form of examination
Course related exam:
• [20-00-1132-pl] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.

Colloquium (optional: including presentation), portfolio, report (optional: including submission of

course material).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1132-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

91
 B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

92
Module name
Teaching Lab - Foundations of Language Technology (FOLT)
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1110 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1110-pl Teaching Lab - Foundations of Language 0 Internship 3
Technology (FOLT) teaching
2 Teaching content
Preparation, organization and correction of a shared tasks. Offering of office hours. Holding of tutorials and
similar tasks in the context of teaching.
3 Learning objectives
After completing the course, the students are able to independently hold a tutorial, conduct shared tasks, and
pursue similar tasks in the context of teaching.
4 Prerequisite for participation
Recommended: participation in previous Foundation of Language Technology (FOLT) courses or similar courses
(e.g. Deep Learning for Natural Language Processing (DL4NLP))
5 Form of examination
Course related exam:
• [20-00-1110-pl] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of
max. two of the following forms is possible. Colloquium (optional: including presentation), portfolio, report
(optional: including submission of course material).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1110-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

93
Module name
Teaching Lab - Natural Language Processing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1127 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1127-pl Teaching Lab - Natural Language Process- 0 Internship 3
ing teaching
2 Teaching content
This module involves supporting a course on Natural Language Processing at the UKP lab. Tasks usually include
creation, presentation, and correction of exercises and programming tasks or projects.
3 Learning objectives
After successful completion of the module, students will be able to:
• Prepare course content from the lecture for home and classroom exercises
• Design and create practical exercises
• Conceive and carry out exercises
• Develop a concept for practical exercises that build on each other
• Apply methods of learning control for the contents of the lecture

4 Prerequisite for participation

Recommended prerequisites: successful completion of the relevant course; good knowledge of Python and
LaTeX
5 Form of examination
Course related exam:
• [20-00-1127-pl] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.

Colloquium (optional: including presentation), portfolio, report (optional: including submission of

course material).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1127-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

94
Module name
Practical Lab in Teaching - Optimization of Static and Dynamic Systems
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1085 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1085-pl Practical Lab in Teaching - Optimization 0 Internship 3
of Static and Dynamic Systems teaching
2 Teaching content

• Elaboration of new exercises and programming assignments

• Concepts for exercise sheets

3 Learning objectives
After successfully completing the course, students can:
• Prepare teaching content from the lecture for home and classroom exercises as well as for programming
tasks accompanying the lecture
• Develop a concept for practical exercises that build on one another
• Apply methods of learning control to the learning content of the lecture

4 Prerequisite for participation

Successful participation in "Optimization of static and dynamic systems" is recommended.
5 Form of examination
Course related exam:
• [20-00-1085-pl] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of
max. two of the following forms is possible. Colloquium (optional: including presentation), portfolio, report
(optional: including submission of course material).
6 Prerequisite for the award of credit points
B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
7 Grading
Course related exam:
• [20-00-1085-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

95
Module name
Practical Lab in Teaching - Statistical Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1070 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. Arjan Kuijper
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1070-pl Practical Lab in Teaching - Statistical Ma- 0 Internship 3
chine Learning teaching
2 Teaching content
Teaching support, such as supervision of exercise groups, consultations, etc.
3 Learning objectives
Preparation for future teachers' own teaching activities.
4 Prerequisite for participation
Successful completion of Statistical Machine Learning or corresponding knowledge.
5 Form of examination
Course related exam:
• [20-00-1070-pl] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1070-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

96
Module name
Teaching Lab - Visual Computing
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0519 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr.-Ing. Michael Gösele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0519-pl Praktikum in der Lehre - Visual Comput- 0 Internship 3
ing teaching
2 Teaching content
Assistance in organizing tutorials for Introduction to Human Computer Systems
3 Learning objectives
Creation and evaluation of teaching materials for courses in computer science and supervision of students.
4 Prerequisite for participation
Visul Computing
5 Form of examination
Course related exam:
• [20-00-0519-pl] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass Exam (100%)
7 Grading
Course related exam:
• [20-00-0519-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

97
Module name
Practical Lab in Teaching - Visual Inference
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1131 5 CP 150 h 105 h 1 Term Every Semester
Language Module owner
German/English Prof. Dr. Arjan Kuijper
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1131-pl Practical Lab in Teaching - Visual Infer- 0 Internship 3
ence teaching
2 Teaching content
Creation of lab exercises and teaching material for courses of the FG Visual Inference
3 Learning objectives
After students have taken the module, they will be able to classify problems in exercises, evaluate them, and
grade them correctly.
4 Prerequisite for participation
Recommended: successful participation of the lecture Computer Vision I (20-00-0157-iv) and/or Computer
Vision II (20-00-0401-iv), depending on the semester.
5 Form of examination
Course related exam:
• [20-00-1131-pl] (Study achievement, Oral examination, Duration: 15 Min., Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible.

Colloquium (optional: including presentation), portfolio, report (optional: including submission of

course material).
6 Prerequisite for the award of credit points
Pass exam 100%.
7 Grading
Course related exam:
• [20-00-1131-pl] (Study achievement, Oral examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

98
Module name
Practical Lab in Teaching: Reinforcement Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1169 5 CP 150 h 105 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1169-pl Practical Lab in Teaching: Reinforcement 0 Internship 3
Learning teaching
2 Teaching content
Support of teaching such as, supervision of exercise groups, office hours, or similar.
3 Learning objectives
Upon successful completion of the module students will have learned how to create and evaluate exercises,
and will acquire professional experience in the organizational, aspects of an advanced course. They will also be
able to further their experience in implementing and understanding problems in Reinforcement Learning by
assisting in the creation of exercises.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-1169-pl] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of
max. two of the following forms is possible. Colloquium (optional: including presentation), portfolio, report
(optional: including submission of course material).
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1169-pl] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

99
1.1.2.3 Labs, Project Labs, Related Courses

Module name
Data Management - Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1041 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1041-pr Data Management - Lab 0 Internship 4
2 Teaching content
Participants independently solve alone or in a small group an individually a given problem. The problems are
usually programming projects inspired by the research performed at the Data Management Lab.

Possible areas are:

- Scalable Databases & Modern Hardware
- Cloud Databases & Blockchains
- Interactive Data and Text Exploration
- Natural Language Interfaces for Databases
- Scalable Systems for Machine Learning

In this lab the students will realise a project defined by their advisor. Compared to the "Data Man-
agement - Lab", the “Data Management - Extended Lab” requires more effort.
3 Learning objectives
After completion of this course the students are able to
- Understand state-of-the-art techniques in modern data management systems
- Apply and implemenation of techniques in individual projects
- Provide experimental evidence for design decisions with benchmarks and/or real workloads
4 Prerequisite for participation
Depending on selected topic.
5 Form of examination
Course related exam:
• [20-00-1041-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1041-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

100
101
Module name
Data Management - Extended Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1042 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1042-pp Data Management - Extended Lab 0 Project 6
2 Teaching content
Participants independently solve alone or in a small group an individually a given problem. The problems are
usually programming projects inspired by the research performed at the Data Management Lab.

Possible areas are:

- Scalable Databases & Modern Hardware
- Cloud Databases & Blockchains
- Interactive Data and Text Exploration
- Natural Language Interfaces for Databases
- Scalable Systems for Machine Learning

In this lab the students will realise a project defined by their advisor. Compared to the "Data Man-
agement - Lab", the “Data Management - Extended Lab” requires more effort.
3 Learning objectives
After completion of this course the students are able to
- Understand state-of-the-art techniques in modern data management systems
- Apply and implemenation of techniques in individual projects
- Provide experimental evidence for design decisions with benchmarks and/or real workloads
4 Prerequisite for participation
Depending on selected topic.
5 Form of examination
Course related exam:
• [20-00-1042-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1042-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

102
Module name
Distributed Systems Programming: Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0985 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Eberhard Mühlhäuser
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0985-pr Distributed Systems Programming: Lab 0 Internship 4
2 Teaching content
The course focuses on research topics in distributed systems (DS) and programming languages for DS. The
offered topics depend on the current research of the DSP group including:
• Software-defined networking (SDN)
• Network function virtualization (NFV) and in-network processing (INP)
• Traffic engineering (TE)
• Network monitoring
• Resource management in datacenters (RMF)
• Big data analytics (Spark, YARN, OpenStack, ..)
• Event-based systems
• Security in SDN, INP, and big data
• Geo-distributed data processing
• Compiler infrastructures for DS
• Language abstractions for DS
• Session types / calculi for DS
• Network Protocols
In this project the students will realize their own/a group research project defined together with their adviser.
Compared to the “DSP: Lab”, the “DSP: Project” requires more effort.
3 Learning objectives
After participating in the course, the student is able to solve and evaluate technical and scientific problems in
designing and developing future DS concepts and applications using state of the art scientific methods.

Acquired competences include (depending on the selected topic):

• Literature research in the project area
• Design of complex DS
• Implementation and verification of components for DS
• Deep understanding of existing complex software systems
• Methodical analysis and evaluation of
– Models
– Experiments
– Software
• Design of programming languages
• Writing of technical documents or project reports
• Research style presentation of the outcomes of the project

4 Prerequisite for participation

103
 Interest to develop solutions for challenging problems of DS, self-motivation and high interest in recent research.

Due to the wide area of topics, we cannot offer a comprehensive list of requirements. All topics are
research-oriented, hence topic-specific background knowledge is required. More details will be given in the
first lecture.
5 Form of examination
Course related exam:
• [20-00-0985-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0985-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

104
Module name
Expert Lab on Robot Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1108 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1108-pp Expert Lab on Robot Learning 0 Project 6
2 Teaching content
In this project, students perfect their ability at experimental work in an interdisciplinary team and become
experts in scientific approaches to Robot Learning. In this project, small groups of students develop a common
experiment in Robot Learning based on special robotic platforms, evaluate it and write a research report/paper
that reaches the quality of a submission to an international scientific conference or journal.
3 Learning objectives
After completing the module, students can apply the practical skills of an expert in scientific studies on Robot
Learning. They are able to analyze and synthesize experiments from the research idea up to the publication.
4 Prerequisite for participation
Recommended: Successful completion of Robot Learning: Integrated Project - Part 1 and Robot Learning:
Integrated Project - Part 2.
5 Form of examination
Course related exam:
• [20-00-1108-pp] (Technical examination, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible. Report (optional: including submission of source code), colloquium
(optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1108-pp] (Technical examination, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

105
Module name
Research Project Knowledge Engineering and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0751 12 CP 360 h 240 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0751-pj Research Project in Knowledge Engineer- 0 Project 8
ing and Machine Learning
2 Teaching content
Through an individual project, students are tutored to autonomously conduct research in knowledge
engineering, artificial intelligence, machine learning or data mining
The research topics will be defined in collaboration with their tutor.

Possible areas:
- Machine Learning and Data Mining
- Inductive Rule Learning
- Learning from Preferences
- Multilabel Classification
- Information Extraction
- Web Mining
- Semantic Web
- Game Playing

Concrete tasks will be assigned on an individual basis. The project can be started at any time.

Students that are interested in such a project, please contact a staff member of the Knowledge Engi-
neering group (http://www.ke.tu-darmstadt.de).
3 Learning objectives
After completion of this project, students should be able to
- autonomously conduct small research projects in the areas knowledge engineering, artificial intelligence,
maschine learning and data mining
- document the achieved results in a report
- present them in a scientific talk
- defend them in a critical discussion
4 Prerequisite for participation
Basic knowledge in Knowledge Engineering , Artificial Intelligence and Machine Learning is helpful.
Java or similar is expected.
Self-motivated and highly interested in actual research.
5 Form of examination
Course related exam:
• [20-00-0751-pj] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading

106
 Course related exam:
• [20-00-0751-pj] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

10 Comment

107
Module name
Advanced Visual Computing Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0537 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0537-pr Advanced Visual Computing Lab 0 Internship 4
2 Teaching content
Students work in this lab on selected advanced topics in the area of visual computing. Project results will be
presented in a talk at the end of the course. The specific topics addressed in the lab change every semester and
should be discussed directly with one of the instructors.
3 Learning objectives
After successful completion of this course, the students will be able to independently analyze and solve an
advanced problem in the area of visual computing and to evaluate the results.
4 Prerequisite for participation
Programming skills, e.g. Java, C++
Basic knowledge in Visula Computing
Participation in at least one basic lectures and one lab in the are of Visual Computing.
5 Form of examination
Course related exam:
• [20-00-0537-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0537-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Will be announced in lecture.
10 Comment

108
Module name
Integrated Robotics Project 1
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0324 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0324-pr Integrated Robotics Project (Part 1) 0 Internship 4
2 Teaching content
- guided independent work on a concrete task from development and application of modern robotic systems
and, as far as possible, as member of a team of developers
- becoming acquainted with the relevant state of research and technology
- development of a solution approach and its implementation
- application and evaluation based on robot experiments or simulations
- documentation of task, approach, implementation and results in a final report and conduction of a final
presentation
3 Learning objectives
Through successful participation students acquire deepened knowledge in selected areas, subsystems and
methods of modern robotic systems as well as in-depth skills for development, implementation, and experimental
evaluation. They train presentation skills and, as far as possible, team work.
4 Prerequisite for participation
- basic knowledge within Robotics as given in lecture “Grundlagen der Robotik”
- programming skills depending on task
5 Form of examination
Course related exam:
• [20-00-0324-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0324-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References
Will be given in lecture.

109
10 Comment

110
Module name
Integrated Robotics Project 2
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0357 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0357-pr Integrated Project (Part 2) 0 Internship 4
2 Teaching content
- guided independent work on a concrete task from development and application of modern robotic systems
and, as far as possible, as member of a team of developers
- becoming acquainted with the relevant state of research and technology
- development of a solution approach and its implementation
- application and evaluation based on robot experiments or simulations
- documentation of task, approach, implementation and results in a final report and conduction of a final
presentation
3 Learning objectives
Through successful participation students acquire deepened knowledge in selected areas, subsystems and
methods of modern robotic systems as well as in-depth skills for development, implementation, and experimental
evaluation. They train presentation skills and, as far as possible, team work.
4 Prerequisite for participation
- basic knowledge within Robotics as given in lecture “Grundlagen der Robotik”
- programming skills depending on task
- Participation in "Integriertes Robotik-Project 1"
5 Form of examination
Course related exam:
• [20-00-0357-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0357-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

111
 Will be given in course.
10 Comment

112
Module name
Robot Learning: Integrated Project - Part 1
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0753 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0753-pj Robot Learning: Integrated Project - Part 0 Project 4
1
2 Teaching content
In "Robot Learning: Integrated Project, Part 1", students will pose a current research problem in the domain
of robot learning with assistance of their advisor. The students will select a robot learning topic to fit their
research interests, on which they will pursue in-depth literature studies. Using these results, they will develop
a plan for their project, try out the algorithms of interest and implement a prototype in simulation.
3 Learning objectives
Upon successful completion of this course, students will be able to independently develop small research
projects in the domain of robot learning and test first research ideas in simulation.
4 Prerequisite for participation
Previous or concurrent participation in the lecture "Robot Learning".
5 Form of examination
Course related exam:
• [20-00-0753-pj] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0753-pj] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

10 Comment

113
Module name
Robot Learning: Integrated Project - Part 2
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0754 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0754-pj Robot Learning: Integrated Project - Part 0 Project 4
2
2 Teaching content
In "Robot Learning: Integrated Project, Part 2", students will complete their approach to the research problem
from Part 1 and apply it to a real robot. A scientific article on the research problem, methods and results will
be written and potentially submitted to a national or international scientific venue.
3 Learning objectives
Upon successful completion of this course, students will be able to independently develop small research
projects in the domain of robot learning and test first research ideas in simulation.
4 Prerequisite for participation
Previous or concurrent participation in the lecture "Robot Learning".
5 Form of examination
Course related exam:
• [20-00-0754-pj] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0754-pj] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

10 Comment

114
Module name
Practical Course in Artificial Intelligence
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0412 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0412-pr Practical Course in Artificial Intelligence 0 Internship 4
2 Teaching content
Students have to work on a concrete practical problem in the area of artificial intelligence and solve it with the
help of tools and techniques that they developed on their own or that are already publicly available.

Note the announcements on the homepage of the KE group regarding this course (http://www.ke.informatik.tu-
darmstadt.de/lehre/)!
In semesters, where this course is not announced on the above pages, there is often the possibility of individual
projects (please ask).
3 Learning objectives
After completion of this practical course, students should be able to
- recognize potential uses of artificial intelligence tools
- select appropriate tools for a given task and apply them to this task
- evaluate and measure the success of the use of such tools
4 Prerequisite for participation
Basic knowledge in artificial intelligence
5 Form of examination
Course related exam:
• [20-00-0412-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0412-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References

10 Comment

115
116
Module name
Visual Computing Lab
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0418 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. Bernt Schiele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0418-pr Lab Visual Computing 0 Internship 4
2 Teaching content
Students work in this lab on selected topics in the area of visual computing. Project results will be presented in
a talk at the end of the course. The specific topics addressed in the lab change every semester and should be
discussed directly with one of the instructors.
3 Learning objectives
After successful completion of this course, the students will be able to independently analyze and solve a
problem in the area of visual computing and to evaluate the results.
4 Prerequisite for participation
Practical programming skills, e.g. Java, C++
Basic knowledge or interest within Visual Computing
Participation in one basic lecture within Visiual Computing
5 Form of examination
Course related exam:
• [20-00-0418-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0418-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

Can be used in other degree programs.

9 References
Will be announced in course.
10 Comment

117
Module name
Practical Lab on Intelligent Robot Manipulation
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1159 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1159-pr Practical Lab on Intelligent Robotic Ma- 0 Internship 4
nipulation: Part I
2 Teaching content
This practical lab is offered in combination with the Advanced Seminar. Students that select this module
should work in a group to implement a pipeline for robotic manipulation based on the methodologies and
papers presented in the Advanced Seminar.

The individual topic will be decided between the lecturer and the students, and it should be imple-
mented in principle in simulation using tools like ROS, Gazebo, and MoveIt! Library.
Depending on the conditions, students may also have the possibility to apply their pipeline to a real robot.
Knowledge of Python is a plus, but students could exercise their skills in programming during the practical lab.
3 Learning objectives
At the end of this practical lab, students will be able to implement a holistic system that can solve robot
manipulation tasks through perception, planning, and control.
4 Prerequisite for participation
Reccommended:
Participation in the Seminar on Intelligent Robotic Manipulation.
5 Form of examination
Course related exam:
• [20-00-1159-pr] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible. Report (optional: including submission of source code), colloquium
(optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%)
7 Grading
Course related exam:
• [20-00-1159-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

118
Module name
Lab on intelligent Robotic Manipulation: : Part II
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-1170 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-1170-pr Lab on intelligent Robotic Manipulation: 0 Internship 4
: Part II
2 Teaching content
In this project, individuals or groups of two-three students are able to gain in depth experience working towards
a scientific project in the area of AI robotic manipulation. The topic is decided between the supervisor and
the students, and it aims towards fundamental progress in the ares of robotic perception, control, planning
and general decision-making for robotic manipulation, mobile manipulation or human-robot interaction. The
students are expected to work in simulation and on real robotic platforms, and collaborate with our team that
has interdisciplinary expertise. The students are expected to write a research report/paper at the quality of a
submission to an international scientific conference or journal, which will be peer-reviewed by our team and
other students.
3 Learning objectives
The students will work on cutting-edge research topics, and will get the opportunity to get a glimpse into
scientific research, from investigating the related literature, to implementing already existing approaches,
developing critical thinking for assessing the quality of obtained results. On a practical level, they will augment
their skills in coding, and they will gain experience with working on real robotic manipulation problems.
4 Prerequisite for participation

5 Form of examination
Course related exam:
• [20-00-1170-pr] (Study achievement, Oral/written examination, Default RS)
The form of the examination will be announced at the beginning of the course. One or a combination of max.
two of the following forms is possible. Report (optional: including submission of source code), colloquium
(optional: including presentation).
6 Prerequisite for the award of credit points
Pass exam (100%).
7 Grading
Course related exam:
• [20-00-1170-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
May be used in other degree programs.
9 References

10 Comment

119
Module name
Practical Exercises for Neural Information Processing for Brain-Computer Interfaces
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0945 6 CP 180 h 120 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0945-pr Practical Exercises for Neural Information 0 Internship 4
Processing for Brain-Computer Interfaces
2 Teaching content
* Lab exercises for signal processing for neuroimaging
* Lab exercises for pattern recognition in neuroimaging
* Lab exercises for Brain-computer interfaces
3 Learning objectives
Based on the lecture "Neural Information Processing for Brain-Computer Interfaces", this lab course provides
students with the practical abilities needed for projects in the domain of neural engineering.
4 Prerequisite for participation
Successful prior completion of the lecture "Neural Information Processing for Brain-Computer Interfaces"
5 Form of examination
Course related exam:
• [20-00-0945-pr] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0945-pr] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

120
Module name
Practical Project Knowledge Engineering and Machine Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0919 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0919-pp Practical Project Knowledge Engineering 0 Project 6
and Machine Learning
2 Teaching content
In the course of this practical project, students implement a larger, predefined task in the areas of knowledge
engineering, artificial intelligence, machine learning or data mining. The topics will be defined in collaboration
with their tutor.

Possible areas:
- Machine Learning and Data Mining
- Inductive Rule Learning
- Learning from Preferences
- Multilabel Classification
- Information Extraction
- Web Mining
- Semantic Web
- Game Playing

Concrete tasks will be assigned on an individual basis. The project can be started at any time.

Students that are interested in such a project, please contact a staff member of the Knowledge Engi-
neering group (http://www.ke.tu-darmstadt.de).
3 Learning objectives
After completion of this project, students should be able to
- autonomously program larger research projects in the areas knowledge engineering, artificial intelligence,
maschine learning and data mining
- conduct scientific experiments and evaluations using the implemented instruments
4 Prerequisite for participation
Basic knowledge in Knowledge Engineering, Artificial Intelligence, Data Mining and Machine Learning.
Basic knowledge in programming (e.g. Java).
Autonomous work and Interest on actual research.
5 Form of examination
Course related exam:
• [20-00-0919-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0919-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

121
8 Usability of the module
B.Sc. Informatik
M.Sc. Informatik
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References

10 Comment

122
Module name
Project Lab Deep Learning in Computer Vision
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0980 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr.-Ing. Michael Gösele
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0980-pp Project Lab Deep Learning in Computer 0 Internship 6
Vision
2 Teaching content
In this project lab groups of students will work on selected topics in deep learning (deep neural networks)
for problems in computer vision. This includes the practical implementation with modern deep learning
frameworks. Results will be presented in a talk at the end of the lab. Concrete topics follow the current state of
the art and change from term to term.
3 Learning objectives
Through their successful participation, students acquire in-depth knowledge on deep neural networks and their
applications in computer vision. They are able to analyze, modify, and apply state-of-the-art techniques in this
area. Moreover, they practice their abilities for presenting their results and for collaboration in teams.
4 Prerequisite for participation
* Solid programming skills in C/C++ or Python or Lua
* Prior or concurrent registration for "Computer Vision I"
5 Form of examination
Course related exam:
• [20-00-0980-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0980-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

123
Module name
Project Lab E-Learning
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0979 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German Prof. Dr. techn. Johannes Fürnkranz
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0979-pp Project Lab E-Learning 0 Internship 6
2 Teaching content
Within the project lab, advanced e-learning content will be created, or existing e-learning elements will be
evaluated and improved. The concrete focus is defined individually together with the supervisor. The range
of topics includes the development of innovative concepts for using Moodle in lectures, the visualisation of
algorithms and data structures, or the development of e-learning units using an authoring software.
3 Learning objectives
After the project lab, participants will have a better understanding of e-learning and more in depth knowledge
about the design and implementation of e-learning that aids learners.
4 Prerequisite for participation
The lab requires good programming skills in Java (or, depending on the chosen topic, the How to Design
Programming Languages used in the FOP lecture, or Moodle), as well as familiarity with standard data
structures and algorithms, for example as taught in the AuD lecture.
5 Form of examination
Course related exam:
• [20-00-0979-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0979-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

124
Module name
Robotics Lab Project
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0248 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
German/English Prof. Dr. rer. nat. Oskar von Stryk
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0248-pp Robotics Project 0 Project 6
2 Teaching content
- guided independent work on a concrete task from development and application of modern robotic systems
and, as far as possible, as member of a team of developers
- development of a solution approach and its implementation
- application and evaluation based on robot experiments or simulations
- documentation of task, approach, implementation and results in a final report and conduction of a final
presentation
3 Learning objectives
Through successful participation students acquire deepened knowledge in selected areas and subsystems
of modern robotic systems as well as in-depth skills for development, implementation, and experimental
evaluation. They train presentation skills and, as far as possible, team work.
4 Prerequisite for participation
- basic knowledge within Robotics as given in lecture “Grundlagen der Robotik”
- programming skills depending on task
5 Form of examination
Course related exam:
• [20-00-0248-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0248-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

B.Sc. Informatik
M.Sc. Informatik
B.Sc. Computational Engineering
M.Sc. Computational Engineering
M.Sc. Wirtschaftsinformatik
B.Sc. Psychologie in IT
Joint B.A. Informatik
B.Sc. Sportwissenschaft und Informatik
M.Sc. Sportwissenschaft und Informatik

May be used in other degree programs.

9 References

10 Comment

125
126
Module name
Data Analysis Software Project for Natural Language
Module nr. Credit points Workload Self-study Module duration Module cycle
20-00-0948 9 CP 270 h 180 h 1 Term Every 2. Semester
Language Module owner
English Prof. Dr. phil. Iryna Gurevych
1 Courses of this module
Course nr. Course name Workload (CP) Teaching form
HPW
20-00-0948-pp Data Analysis Software Project for Natural 0 Internship 6
Language
2 Teaching content
Big datasets have turned to highly valuable information sources nowadays. Intelligent data analysis is the key
to unlock their actual value. Such analysis can help to obtain new and useful information and support decision
making processes. In this project, students will develop own ideas and build novel software systems to extract
useful information from a given dataset of natural language text, i.e. textual Big-Data.

The topic of each semester‘s course can be found on the course website at https://www.ukp.tu-
darmstadt.de/teaching/courses/software-project/
3 Learning objectives
After completion of the project, the students are able to
- understand practical aspects for natural language processing
- develop own NLP-systems,
- analyze big datasets of natural language text, and
- use state-of-the-art frameworks and technology for natural language processing.
4 Prerequisite for participation
- Programming skills (Scala, Java or Python)
- Interest in working with natural language text
5 Form of examination
Course related exam:
• [20-00-0948-pp] (Study achievement, Oral/written examination, Default RS)

6 Prerequisite for the award of credit points

Pass exam (100%)
7 Grading
Course related exam:
• [20-00-0948-pp] (Study achievement, Oral/written examination, Weighting: 100 %)

8 Usability of the module

9 References

10 Comment

127
1.2 Studium Generale

128