SYLLABUS

1. Data about the program

1.1 Higher education Babeş – Bolyai University

institution
1.2 Faculty Faculty of Psychology and Educational Sciences
1.3 Department Department of Psychology
1.4 Field of study Psychology - Cognitive Science
1.5 Study cycle Bachelor
1.6 Study program / Psychology - Cognitive Sciences/ Bachelor in Psychology
Qualification

2. Discipline data
2.1 Name of the discipline Artificial Intelligence
2.2 Teacher in charge
Lect. Dr. Mircea Ioan-Gabriel
2.3 Teacher in charge
Lect. Dr. Mircea Ioan-Gabriel
2.4 Year of study I 2.5 Semester 2 2.6. Type of E 2.7 Discipline regime DS
evaluation

3. Estimated total time (hours per semester of teaching activities)

3.1 Number of hours per week 3 Of which: 3.2 course 2 3.3 seminar / laboratory 1
3.4 Total hours in the curriculum 42 Of which: 3.5 28 3.6 seminar / 14
course laboratory
Distribution of time: Hours
Study by textbook, course support, bibliography, and notes 20
Additional documentation in the library, on specialized electronic platforms and in the field 13
Preparation of seminars / laboratories, topics, papers, portfolios, and essays 20
Tutorship 1
Evaluations 2
Other activities: research activities 2
3.7 Total hours of individual study 58
3.8 Total hours per semester 100
3.9 Number of ECTS credits 4

1. Prerequisites (if necessary)

4.1. curriculum • mathematical analysis, data structures and algorithms, problem
solving, statistics
4.2. competencies Object oriented programming competencies, algorithmic
reasoning, logical reasoning
1. Conditions (if necessary)
5.1. for the course •
5.2. for the seminar / lab
•
activities

2. Specific competencies acquired

 Application of efficient and rigorous knowledge of artificial
intelligence, showing responsible attitudes toward the scientific and
Professional didactic fields, respecting the professional and ethical principles.
competencies

 Use of efficient methods and techniques for learning,

information, research and development of abilities for
Transversal knowledge exploitation, for adapting to the needs of a dynamic
competencies society and for communication in Romanian as well as in a
widely used foreign language
 Use of efficient methods and techniques to learn, inform, research
and develop the abilities to value the knowledge, to adapt to
requirements of a dynamic society and to communicate in
Romanian language and in a language of international circulation

3. Objectives of the discipline (outcome of the acquired competencies)

7.1 General objective  Acquiring solid knowledge regarding core theoretical concepts and
of the discipline models that explain artificial intelligence
 Understanding how a computer that can learn, plan, and solve
problems autonomously
 Acquiring a rigorous and scientific framework applying artificial
intelligence

1. Knowledge and understanding

 Defining the evolution of AI and understanding the concepts of
7.2 Specific objective machine learning and other concepts, tools, and techniques to build
of the discipline intelligent systems
2. Explaining and interpretation
 Understanding the factors that influence AI algorithms in real-life
3. Instrumental
 Developing the ability to propose, evaluate, and implement
solutions to problems requiring AI techniques
4. Attitude
 Developing an ethical attitude towards using AI
4. Content
8.1 Course Teaching methods Remarks
1. AI : Past, Present and Future - An introduction Interactive exposure
Historical evolution of AI Explanation
An ontology of AI Conversation
Didactical demonstration

2. Teaching the machine: supervised classification - Interactive exposure

Perceptron, Artificial Neural Network Explanation
Conversation
Didactical demonstration

3. Teaching the machine: supervised regression - Interactive exposure

Artificial Neural Network Explanation Conversation
Didactical demonstration

4. Teaching the machine: clustering and Interactive exposure

association,dimensionality reduction - Explanation Conversation
KNN, K-means, SOM, PCA. Didactical demonstration
Data visualization and preprocessing

5. Training and evaluating Machine Learning Interactive exposure

Models. Loss. Overfitting Explanation Conversation
Didactical
demonstration

6. Properly Searching for Solutions: Backtracking, Interactive exposure

DFS, BFS, A*, GAs, ACO - TSP Explanation Conversation
Constraint Satisfaction Problems: Didactical demonstration
one player games Sudoku

7. Reinforcement Learning Interactive exposure

Explanation Conversation
Didactical demonstration
8. Game Theory and Estimation Theory Interactive exposure
more player games Explanation Conversation
Hidden Markov Models Didactical demonstration
9. Going deeper into the Rabit Hole: The quest for Interactive exposure
the Real AI Explanation Conversation
Deep Neural Networks - Main Ideas Didactical demonstration
CNNs, RNNs,
10. The Imitation Game: Mimicking Humanity Interactive exposure
Spiking Nets, NLP, R-CNNs, Autoencoders, GANs Explanation Conversation
Didactical demonstration
11. Deploying and embedding AI algorithms in Interactive exposure
Real-Life: Computational Challenges, Intelligent Explanation Conversation
IoT, Robots, Autonomous Driving Didactical demonstration
 12. The Present and Future of AI : Ethical Aspects Interactive exposure
Explanation Conversation
Didactical demonstration
Bibliography
Programming Fundamentals
1. Donald E. Knuth. 2011. The Art of Computer Programming: Combinatorial Algorithms,
Part 1 (1st. ed.). Addison-Wesley Professional.
2. Brian W. Kernighan and Dennis M. Ritchie. 1988. The C Programming Language (2nd.
ed.). Prentice Hall Professional Technical Reference.
3. Bruce Eckel. 2000. Thinking in C++, Volume I: Introduction to Standard C++, Second
Edition (2nd. ed.). Prentice Hall PTR, USA.
4. Dijkstra, Edsger W. A Discipline of Programming. 1976.
5. Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. 2009.
Introduction to Algorithms, Third Edition (3rd. ed.). The MIT Press.
6. Thomas H. Cormen. 2013. Algorithms Unlocked. The MIT Press.
7. Antti Laaksonen, Guide to Competitive Programming - Learning and Improving Algorithms
Through Contests, Second Edition. Undergraduate Topics in Computer Science, Springer
2020, ISBN 978-3-030-39356-4, pp. 1-296

Artificial Intelligence
1. Stuart Russell and Peter Norvig. 2009. Artificial Intelligence: A Modern Approach (3rd.
ed.). Prentice Hall Press, USA.
2. Géron, Aurélien. Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow:
Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd ed., O’Reilly, 2019.
3. David James. 2018. Introduction to Machine Learning with Python: A Guide for Beginners
in Data Science (1st. ed.). CreateSpace Independent Publishing Platform, North Charleston,
SC, USA.
4. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. The MIT
Press.

IoT
1. Dimitrios Serpanos and Marilyn Wolf. 2017. Internet-of-Things (IoT) Systems:
Architectures, Algorithms, Methodologies (1st. ed.). Springer Publishing Company,
Incorporated.
2. Samuel Greengard. 2015. The Internet of Things. The MIT Press.

Scientific Research
1. Justin Zobel. 2015. Writing for Computer Science (3rd. ed.). Springer Publishing Company,
Incorporated.
2. Philip W.L. Fong. 2009. Reading a computer science research paper. SIGCSE Bull. 41, 2
(June 2009), 138–140. DOI:https://doi.org/10.1145/1595453.1595493
3. Lury, Celia. Routledge Handbook of Interdisciplinary Research Methods. , 2018.
4. Repko, Allen F, et al. Case Studies in Interdisciplinary Research. Thousand Oaks, CA:
SAGE Publications, Inc., 2012. SAGE Research Methods. 13 Jan 2021, doi:
http://www.doi.org/10.4135/9781483349541
5. Repko, Allen F, Rick Szostak, and Michelle P. Buchberger. Introduction to Interdisciplinary
Studies. , 2017.
6. Repko, Allen F, and Rick Szostak. Interdisciplinary Research: Process and Theory. , 2017.
8.2 Seminar / laboratory Teaching methods Remarks
Seminar
The goal of the seminar is to familiarize the
student to the scientific method of documentation
and research and to address the topics presented at
the courses by tackling concrete case studies.
Each student will select a thematic during the
semester. At each of the seminaries several students
will present their essay on the given thematic by
analysing the literature and expressing their own
opinions of the matter at hand. The other students
should all pick at least one of the papers presented
that day, and in the week preceding the presentation
of the paper have to comment on the what can be
improved in a peer-review fashion. The seminar
grade is the average from the grade obtained for the
presentation and the grade for the assessment of
other papers during the semester
Laboratories
Labs are viewed as workshops. The assignments
are submitted on git and graded by the teacher. The
student is informed of his grading in a detailed
manner. Students can contest the grades on their
assignments at the beginning of the lab.
The first lab represents workshops concerning Lab assignment
the implementation, from scratch, of a perceptron Explanation
for the machine learning of the AND logical Conversation
operation and then of a minimalistic ANN for the
Scientific method
machine learning of the XOR logical operation.
HW:implement an ANN from scratch for the
fulladder of two bits and two bits
The second lab focuses on the employment of the
ANN for solving regression problems, loss
computation and mainly on the entire flow : data
preprocessing and analysis -> training (and
validation) -> testing. Also the supervised methods
of ML are compared and contrasted against
unsupervised implementations. a SOM
implementation is given as part of the workshop
HW:train an ANN for nonlinear regression
and a KNN for clustering on the iris dataset
(with tools)
 The third lab focuses on searching algorithms: Lab assignment
having TSP as the problem to beat, we discuss one Explanation
by one the implementation of the bruteforce Conversation
approach, the branch&bound and the simulated Scientific method
annealing. Also an implementation for a genetic
algorithm is given but it is not used on the TSP
problem.
HW: employ the genetic algorithm to solve the
TCP
The fourth lab tackles decision making in the
context of uncertainty and probability. The
workshop covers the implementation of a decision
tree and the basis of fuzzy sets and variables. Also,
an implementation of a Hidden Markov Model is
given.
HW: transform the decision tree implemented
in the workshop into a fuzzy decision tree using
the already implemented fuzzy constructs

The last two workshops won’t cover actual Lab assignment

implementations. Their purpose is to illustrate the Explanation
proper usage of the most popular industrial Conversation
frameworks in the deep learning realm : tensorflow,
keras, pytorch, etc. as well as spectacular products Scientific method
at work.
HW:run two or three methods of solving on
the same problem and construct a table of
performance comparison between the techniques
on the same benchmark

5. Corroborating the content of the discipline with the expectations of the epistemic
community, professional associations and representative employers within the field of
the program

The course follows the IEEE and ACM curricular recommendations for computer science studies

6. Evaluation
Type of activity 10.1 Evaluation criteria 10.2 Evaluation methods 10.3 Share in the grade
(%)
10.4 Course Proper understanding Final Written 25%
of scientific research Exam+Quizzes
methodologies in (Good quizzes answers
Computer Science can boost the written
Proper scientific ethics
exam grade with one
point)
10.5 Seminar / lab Framework design Scientific Essay 15%
activities and architecture.
Programming
principles and
practices. Testing.
 Software application Peer Review 15%
design. Programming
principles and
practices. Testing.
IoT software design. Lab Homework 45%
Programming (5 Assignments)
principles and
practices. Testing.
10.6 Minimum performance standards
• Minimum 5 grade for the course and lab activity

Date Signature of course coordinator Signature of seminar coordinator

16.12.2021 Lect. Dr. Mircea Ioan-Gabriel Lect. Dr. Mircea Ioan-Gabriel

Date of approval Signature of the head of department

..........................