POST GRADUATE DEGREE COURSE

M.TECH
IN
ARTIFICIAL INTELLIGENCE
&MACHINE LEARNING
[W.E.F. 2021-22]

DEPARTMENT OF
COMPUTER SCIENCE AND SYSTEMS
ENGINEERING
AU COLLEGE OF ENGINEERING
(AUTONOMOUS)
ANDHRA UNIVERSITY
VISAKHAPATNAM-530 003
 ANDHRA UNIVERSITY: VISAKHAPATNAM
M.Tech
Artificial Intelligence & Machine Learning
Course Structure and Scheme of Valuation w.e.f. 2021-2022

I-SEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.

MTAIML11 Mathematicas for Machine Learning 3 - 70 30 100 3

MTAIML12 Artificial Intelligence 3 - 70 30 100 3

MTAIML13 Elective-I 3 - 70 30 100 3
MTAIML14 Elective-II 3 - 70 30 100 3
MTCST15 Research Methodology &IPR 3 - 70 30 100 2
MTCST16 Organizational Behavior
3 - 70 30 100 0
(Audit Course)
MTAIML17 Artificial Intelligence Lab - 3 50 50 100 2
MTAIML18 Data mining Lab using Python - 3 50 50 100 2
Total 18 6 520 280 800 18

Elective-I: Data Mining/Cloud Computing/Evolutionary Computing

Elective II: Big Data Analytics/Internet of Things/Pattern Recognition

II-SEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIML21 Machine Learning 3 - 70 30 100 3
MTAIML22 Soft Computing 3 - 70 30 100 3
MTAIML23 Elective-III 3 3 - 70 30 100 3
MTAIML24 Elective-IV 3 - 70 30 100 3
MTCST25 Entrepreneurship (Audit Course) 3 - 70 30 100 0
MTAIML26 Machine Learning Lab - 3 50 50 100 2
MTAIML27 Soft Computing Lab - 3 50 50 100 2
MTAIML28 Mini Project With Seminar - 3 - 100 100 2
Total 15 9 450 350 800 18
Elective-III: Computer Vision/Natural Language Processing/Recommender Systems
Elective-IV: Robotics and Intelligent Systems/Reinforcement Learning/NoSQL Databases
 III-SEMESTER

Periods/week Max. Marks

Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIMLR31 Elective-V 3 - 70 30 100 3
MTAIMLR32 Open Elective 3 - 70 30 100 3
MTAIMLR33 Dissertation-I / Industrial project - 100 - 100 10
Total 6 - 240 60 300 16

Elective V : Deep Learning/Expert Systems/High Performance Computing

Open Elective :Business Analytics/Operations Research/Social Media Analytics

IVSEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTCSTAIR41 Dissertation - II - - 100 - 100 16
Total - - 100 - 100 16
 M.TECH (CSE-AI&ML)

Programme Education Objectives (PEO)

PEO 1: To drive the students to achieve excellence in research and professional career.
PEO 2: To promote creative thinking and innovative mindset for solving societal problems.
PEO 3: To help exhibit adaptive and agile skills in the core area of Artificial Intelligence and
Machine Learning to meet the technical and managerial challenges.
PEO 4: To demonstrate interpersonal skills, professional ethics to work in a team to make a
positive impact on society and sustenance.

PROGRAM OUTCOMES (PO’S)

PO-1 Apply the knowledge of Machine learning, AI and other related

subjects to developsoftware solutions .
PO-2 Able to assess the significance of a complex AI problem and analyse
its characteristics
PO-3 Able to Compare the approaches applicable to solve a complex
problem and identify an effective solution for the societal and
environmental constraints.
PO-4 Able to grasp the essence of the latest research findings related to AI
and Machine learning domain.
PO-5 Able to apply modern tools and algorithms for problem solving and
validate the results through scientific approach.
PO-6 Acquire professional integrity and ethics, understand the participate in
sustainable development of the society

PO-7 Able to work effectively as a multidisciplinaryteam .

PO-8 Able to create reports and make effective presentations .
PO-9 Be able to learn life-long learning skills in pace with the
technological advancements

PROGRAM SPECIFIC OUTCOMES (PSO’S)

PSO-1 An ability to build AI systems capable of automated reasoning for

solving complex problems in a wide range of application domains
PSO-2 Ability to apply ML algorithms for model building towards smart
computing.
PSO-3 Ability to integrate multi-disciplinary approaches to design, develop,
implement and evaluate solutions for various real world problems

1
 MATHEMATICAL FOR MACHINE LEARNING
MTAIML11

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Gain foundation in mathematical concepts related to Linear algebra necessary for ML.
 Understands the concepts related to Orthogonality and rotations.
 Learns different forms of matrix decompositions.
 Understands the concepts of differentiation for finding gradients and curvatures.
 Learns various optimization methods.

Course Outcomes:
At the end of the course, student will be able to
 Attains the capability to solve linear equations and define mappings.
 Extract latent orthogonal features from the set of examples using PCA / SVD
 Estimate the gradients of matrices to apply back propagation and other techniques for
parameter update.
 Capable of estimating the summary statistics of datasets and select appropriate model
to fit the data.

ARTIFICIAL INTELLIGENCE
MTAIML12

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Gain a historical perspective of Artificial Intelligence (AI) and its foundations.
 Become familiar with basic principles of AI toward problem solving, inference,
perception, knowledge representation, and learning.
 Investigate applications of AI techniques in intelligent agents, expert systems, artificial
neural networks and other machine learning models.
 Experience AI development tools such as an ‘AI language’, expert system shell, and/or
data mining tool. Experiment with a machine learning model for simulation and
analysis.
 Explore the current scope, potential, limitations, and implications of intelligent systems.

Course Outcomes:
At the end of the course, student will be able to
 Demonstrate knowledge of the building blocks of AI as presented in terms of intelligent
agents.
  Analyze and formalize the problem as a state space, graph, design heuristics and select
amongst different search or game-based techniques to solve them.
 Develop intelligent algorithms for constraint satisfaction problems and design
intelligent systems for Game Playing.
 Attain the capability to represent various real life problem domains using logic-based
techniques and use this to perform inference or planning.
 Solve problems with uncertain information using Bayesian approaches .

MTAIML13 ELECTIVE-I DATA MINING

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Outcomes:
After the completion of the course, student will be able to:
 Compare types of data, quality of data, suitable measures required to perform data
analysis.
 Choose appropriate classification technique to perform classification, model building
and evaluation.
 Make use of association rule mining techniques on categorical and continuous data
 Identify and apply clustering algorithm (with open-source tools), interpret, evaluate and
report the result.
 Analyze and Compare anomaly detection techniques.

Course Outcomes:
By the end of the course, the student should be able to:
• understand the differences between OLTP and OLAP.
• The student learns how data cube technology supports summarization and
querying high dimensional data.
• The student is introduced to similarity, distance, information gain and other
performance and error metrics used for evaluation of mining results.
• The student is introduced to various approaches to association rule mining,
supervised and unsupervised learning and the corresponding classification and
clustering approaches involving decision trees, Bayesian approaches, model based
and agglomerative approaches.

ELECTIVE-I CLOUD COMPUTING

MTAIML13

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

 Course Objectives:
 To implement Virtualization
 To implement Task Scheduling algorithms.
 Apply Map-Reduce concept to applications.
 To build Private Cloud.
 Broadly educate to know the impact of engineering on legal and societal issues involved.

Course Outcomes:
At the end of the course, student will be able to
 Interpret the key dimensions of the challenge of Cloud Computing
 Examine the economics, financial, and technological implications for selecting cloud
computing for own organization.
 Assessing the financial, technological, and organizational capacity of employer’s for
actively initiating and installing cloud-based applications
 Evaluate own organizations’ needs for capacity building and training in cloud computing-
related IT areas.
 Illustrate Virtualization for Data-Center Automation.

MTAIML14 ELECTIVE-II BIG DATA ANALYTICS

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
This course is aimed at enabling the students to
 Provide an overview of an exciting growing field of big data analytics.
 Introduce the tools required to manage and analyze big data like Hadoop, NoSQL,
Map Reduce, HIVE, Cassandra, Spark.
 Teach the fundamental techniques and principles in achieving big data analytics with
scalability and streaming capability.
 Optimize business decisions and create competitive advantage with Big Data
analytics.
Course Outcomes:
After the completion of the course, student will be able to
 Illustrate on big data and its use cases from selected business domains.
 Interpret and summarize on NoSQL, Cassandra
 Analyze the HADOOP and Map Reduce technologies associated with big data
analytics and explore on Big Data applications Using Hive.
 Make use of Apache Spark, RDDs etc. to work with datasets.
 Assess real time processing with Spark Streaming.
 ELECTIVE-II INTERNET OF THINGS
MTAIML14

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Vision and Introduction to Internet of Things (IoT).
 Understand IoT Market perspective.
 Data and Knowledge Management and use of Devices in IoT Technology.
 Understand State of the Art – IoT Architecture.
 Understand Real World IoT Design Constraints, Industrial Automation and
Commercial.
Course Outcomes (COs):
At the end of the course, student will be able to
 Explain in a concise manner how the general Internet as well as Internet of
Things work.
 Understand constraints and opportunities of wireless and mobile networks for
Internet of Things.
 Use basic sensing and measurement and tools to determine the real-time
performance of network of devices.
 Develop prototype models for various applications using IoT technology.

MTAIML14 ELECTIVE-II PATTERN RECOGNITION

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
From the course the student will learn
 Concepts of Algorithms, Searching and Sorting techniques, Trees, Binary trees,
representation, traversal.
 Dictionaries, ADT for List, Stack, Queue, Hash table representation, Hash
functions, Priority queues, Priority queues using heaps, Search trees.
 AVL trees, operations of AVL trees, Red- Black trees, Splay trees, comparison
of search trees.
Course Outcomes:
After the completion of the course, student will be able to
 Ability to write and analyze algorithms for algorithm correctness and
 efficiency.
 Master a variety of advanced Abstract Data Type (ADT) and data structures
and their Implementation.
 Demonstrate various searching, sorting and hash techniques and be able to
apply and solve problems of real-life.
 Design and implement variety of data structures including linked lists, binary
trees, heaps, graphs and search trees.
 Ability to compare various search trees and find solutions for IT related
problems.

RESEARCH METHODOLOGY AND IPR

MTAIML15

Instruction: 3Periods/week, Time: 3 Hours Credits: 2

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 To provide students a comprehensive knowledge about IPR.
 The students will learn the procedure of obtaining Patents, Copyrights, Trademarks &
Industrial Design.
 To enable the students to know about various IP rights its recognition and protection.
 To provide knowledge on various types of IP databases.
Course Outcomes:
On successful completion of this course student will be able to
 Distinguish and explain various forms of IPRs like trademark, copy right, Geo tagged
etc.
 Know and identify the methods to fit one's own intellectual work in particular form of
IPRs.
 Apply statutory provisions to protect a particular form of IPRs.
 Understand current and emerging issues relating to the intellectual property and its
protection.

MTAIML16 ORGANIZATIONAL BEHAVIOR (AUDIT COURSE)

Instruction: 3Periods/week, Time: 3 Hours Credits: 0

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
  To understand the basic concepts of organizational behavior, its foundations and
importance.
 To enable students to have a basic perspective of Motivation and Motivation theories.
 To acquaint the students about group behavior in organizations, including
communication, leadership conflicts and organizational change and how these are
linked to and impact organizational performance.

Course Outcomes:
 Identifying fundamental aspects of organizational dynamics.
 Evaluate main theories of motivation and formulating suitable motivational strategies.
 Analyze the behavior of individuals and groups in organizations.
 Understanding of Leadership theories and Leadership behavior.
 Apply relevant theories, concepts to address important Organizational Behavior
questions.

ARTIFICIAL INTELLIGENCE LAB

MTAIML17

Instruction: 3Periods/week, Time: 3 Hours Credits: 2

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 To provide a strong foundation of fundamental concepts in Artificial Intelligence.
 To provide a basic exposition to the goals and methods of Artificial Intelligence.
 To apply the techniques in applications which involve perception, reasoning and
learning.
Course Outcomes:
Upon successful completion of the course, the student will be able to:
 Apply the basic principles of AI in problem solving using LISP/PROLOG/
PYTHON
 Implement different state space search algorithms for Game playing using
LISP/PROLOG
 Develop an Expert System using JESS/PROLOG

MTAIML18 DATA MINING LAB USING PYTHON

Instruction: 3Periods/week, Time: 3 Hours Credits: 2

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
  To study the various data analysis techniques in PYTHON Programming language.
 To apply the various data mining techniques available for generating Knowledge such
as association Analysis, Classification and Clustering to various standard datasets and
own datasets.

Course Outcomes:
 Student will be able to write PYTHON programs to perform several data analytics
operations on datasets.
 Ability to extract patterns by applying appropriate data mining techniques from
different types of datasets.

MACHINE LEARNING
MTAIML21

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
Machine Learning course will
 Develop an appreciation for what is involved in learning from data.
 Study a wide variety of learning algorithms.
 Demonstrate how to apply a variety of learning algorithms to data.
 Demonstrate how to perform evaluation of learning algorithms and model selection.

Course Outcomes:
After the completion of the course, student will be able to
 Understand the distribution and diversity of Data.
 Extract features useful for building predictive models.
 Gain knowledge on Supervised and unsupervised Learning techniques.
 Analyze Statistical learning techniques and Logistic Regression
 Select appropriate Support Vector Machines and Perceptron Algorithm
 Compare the performance of different learning models.

SOFT COMPUTING
MTAIML22

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Aims to provide comprehensive understanding of soft computing approaches for AI problem
solving
 Develops in depth knowledge on concepts related to different types of neural networks.
 Provides in depth knowledge on concepts related to Fuzzy logic, membership value assignment
 and reasoning with fuzzy quantities.
 Helps to understand the development of Fuzzy Inference systems and Fuzzy expert systems.
 Introduces the concepts related to Genetic algorithms for learning from examples.

Course Outcomes:
After completion of course, students would be able to:
 Build neural networks to extract patterns from data.
 Build fuzzy inference systems and develop fuzzy expert systems.
 Write genetic algorithms for learning the hyper parameters for data classification.

MTAIML23 ELECTIVE-III COMPUTER VISION

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objective:
To Recognize and describe both the theoretical and practical aspects of computing with images and to
Connect issues from Computer Vision to Human Vision

Course Outcomes:
 Introduce computer vision including fundamentals of image formation.
 Enumerate the concepts of Feature detection and Matching.
 Discuss about Image Segmentation Techniques
 Discuss applications of Feature based alignment like pose estimation.
 Discuss different recognition techniques.

MTAIML23 ELECTIVE-III NATURAL LANGUAGE PROCESSING

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
This course introduces the fundamental concepts and techniques of natural language processing
(NLP).
 Students will gain an in-depth understanding of the computational properties of natural
languages and the commonly used algorithms for processing linguistic information.
 The course examines NLP models and algorithms using both the traditional symbolic and
the more recent statistical approaches.
 Enable students to be capable to describe the application based on natural language
processing and to show the points of syntactic, semantic, and pragmatic processing.

Course Outcomes:
After completion of this course
 Demonstrate a given text with basic Language features.
 To design an innovative application using NLP components
 Explain a rule-based system to tackle morphology/syntax of a language
 To design a tag set to be used for statistical processing for real-time applications.
 To compare and contrast the use of different statistical approaches for different types
of NLP applications.

ELECTIVE-III RECOMMENDER SYSTEMS

MTAIML23

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
This course covers the basic concepts of recommender systems, including personalization algorithms,
evaluation tools, and user experiences

Course Outcomes:
 Describe basic concepts behind recommender systems.
 Explain a variety of approaches for building recommender systems.
 Describe system evaluation methods from both algorithmic and users’ perspectives.
 Describe applications of recommender systems in various domains

ELECTIVE-IV ROBOTICS AND

MTAIML24 INTELLIGENT SYSTEMS
Instruction: 3Periods/week Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objective:
To understand the use of robotics in building intelligent systems.
Course Outcomes:
 Enumerate the fundamentals of robotics and Artificial Intelligence (AI).
 Demonstrate how to set up a Robot.
 Discuss about the practical Robot Design Process.
 Discuss Object Recognition Using Neural Networks and Supervised Learning

ELECTIVE-IV REINFORCEMENT LEARNING

MTAIML24
Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objective:
To provide the fundamentals of Reinforcement learning.

Course Outcomes:
 Enumerate the elements of Reinforcement Learning
 Solve the n-armed Bandit problem.
 Compare different Finite Markov Decision Process
 Discuss about Monte Carlo Methods in solving real world problems.
 List the Applications and Case Studies of Reinforcement Learning

ELECTIVE-IV NoSQL DATABASES

MTAIML24

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Define NoSQL, its characteristics and history, and the primary benefits for using
NoSQL data.
 To Define the major types of NoSQL databases including a primary use case and
advantages/disadvantages of each type
 Create wide-column, document, key-value, graph and object-oriented databases, add
content, and run queries 3.
 Describe the NoSQL data architecture patterns.
 Perform basic database administration tasks.
 Develop NoSQL desktop and cloud database solutions.
Course Outcomes:
By the end of the course, the student will be able to:
 Enumerate different features of NOSQL Databases
 Compare different data models.
 Design a Key-Value Database for a real-world problem.
 Design a Document Database for a real-world problem.
 Design a Graph Database for a real-world problem.

ENTREPRENEURSHIP
MTAIML26

Instruction: 3Periods/week, Time: 3 Hours Credits: 0

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
  To familiarize the students with the concepts of Management.
 To relate the concepts of Management with industrial organizations.
 To explain the factors affecting productivity and how productivity can be increased in
an Industrial undertaking.
 To set forth a basic framework for understanding Entrepreneurship.
Course Outcomes:
On completion of the course, the students will be able to:
 Understand the roles, skills, and functions of management.
 Distinguish the different types of business organizations.
 Identify the factors involved in Production Operations Management.
 Diagnose organizational problems and take suitable decisions.
 Establish good Human Resource Management practices.
 Acquire necessary knowledge and skills required for organizing and carrying out
entrepreneurial activities.

MACHINE LEARNING LAB

MTAIML26

Instruction: 3Periods/week, Time: 3 Hours Credits: 2

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 To learn how to apply machine learning algorithms in real world.
 To gain knowledge about appropriate machine learning algorithms suitable for the
given problem.
 To understand and interpret results of different machine learning algorithms.

Course Outcomes:
On completion of this course, the student will be able to
 Implement machine learning algorithms to real world problems.
 Choose appropriate machine learning algorithm for a problem.
 Interpret the results of two different machine learning algorithms.

SOFT COMPUTING LAB

MTAIML27

Instruction: 3Periods/week, Time: 3 Hours Credits: 2

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 To learn concepts of neural networks to solve real world problems.
  To understand and implement appropriate pre trained models.
 To gain knowledge about genetic algorithms.
Course Outcomes:
On completion of this course, the student will be able to
 Implement neural networks to solve real world problems.
 Choose appropriate pre-trained model to solve real time problem.
 Parameter tuning using Genetic algorithms.

MTAIML31 ELECTIVE-V DEEP LEARNING

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
The objective of this course is to cover the review of ML, fundamentals of feed forward neural
networks, regularization methods and optimization in deep models as well as some advanced
topics such as convolutional neural networks, recurrent neural networks, long short term
memory cells.
Course Outcomes
After completion of course, students would be able to:
 Explore feed forward networks and Deep Neural networks.
 Mathematically understand the deep learning approaches and paradigms
 Complex feature extraction with CNN and RNNs
 Apply the deep learning techniques for various applications.

MTAIML31 ELECTIVE-V HIGH PERFORMANCE COMPUTING

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
The objective of the subject is to
 Introduce the basic concepts related to HPC architecture and parallel computing.
 Discuss various computational techniques for studying soft matter systems.
 Apply these concepts to examine complex bio molecular/materials systems that
generally require large-scale HPC platform with hybrid CPU-GPU architectures.

Course Outcomes: After completion of this course

 Design, formulate, solve, and implement high performance versions of standard
single threaded algorithms.
 Demonstrate the architectural features in the GPU and MIC hardware accelerators.
  Design programs to extract maximum performance in a multicore, shared memory
execution environment processor.
 Analyze Symmetric and Distributed architectures.
 Develop and deploy large scale parallel programs on tightly coupled parallel systems
using the message passing paradigm.

MTAIML32 OPEN ELECTIVE BUSINESS ANALYTICS

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course objectives:
 To introduce students to problem solving with Business Analytics and the use of
spreadsheets for descriptive analytics, data queries and visualization
 To introduce students to statistical sampling, sampling distributions, confidence
intervals and statistical inference
 To familiarize students with various types of regression including simple linear
regression and multiple linear regression
 To introduce students to key concepts in statistical forecasting models for time series
data.
 To familiarize students with predictive decision modeling, model analysis and
developing spreadsheet applications including building linear optimization models on
spreadsheets.

Course outcomes:
After completion of the course the student should be able to:
 Describe data and models used for Business Analytics and apply various descriptive
analytic techniques to analyze data.
 Estimating population parameters, interval estimates, construct confidence intervals and
perform hypothesis testing.
 Estimate and interpret the parameters of simple linear regression and multiple linear
regressions.
 Apply forecasting models for various time series data including stationary time series,
time series with linear trend and time series with seasonality.

MTAIML32 OPEN ELECTIVE OPERATIONS RESEARCH

Instruction: 3Periods/week, Time: 3 Hours Credits: 3

Internal: 30 Marks External: 70 Marks Total: 100 Marks

Course Objectives:
 Formulate a real-world problem as a mathematical programming model.
 Implement and solve the model in EXCEL and LINDO
 Understand the theoretical workings of the simplex method for linear programming and
perform iterations of it by hand.
 Understand the relationship between a linear program and its dual, including strong
duality and complementary slackness.
 Perform sensitivity analysis to determine the direction and magnitude of change of a
model’s optimal solution as the data change.
 Solve specialized linear programming problems like the transportation and assignment
problems.
 Solve network models like the shortest path, minimum spanning tree, and maximum
flow problems.
 Understand the applications of basic methods for, and challenges in integer
programming.
Course Outcomes:
By the end of the course, the student will be able to:
 Students will be able to describe characteristics and scope of OR.
 Students will be able to define and formulate mathematical problems.
 Students will be able to select optimal problems solving techniques for a given problem
using LP.
 Students will be able to formulate and solve transportation, travelling salesman and
transshipment problems.
 Students will be able to formulate and solve optimization problems related to job/ work
assignments.
 Students will be able to demonstrate and solve simple models of Game theory.
 Students will be able to evaluate optimum solution using dynamic programming for
different applications.
 Students will be able to choose / devise appropriate queuing model for practical
application.
 Students will be able to solve different problems related to Network.
POST GRADUATE DEGREE COURSE
M.TECH
IN
ARTIFICIAL INTELLIGENCE
&MACHINE LEARNING
[W.E.F. 2021-22]

DEPARTMENT OF
COMPUTER SCIENCE AND SYSTEMS
ENGINEERING
AU COLLEGE OF ENGINEERING
(AUTONOMOUS)
ANDHRA UNIVERSITY
VISAKHAPATNAM-530 003
 ANDHRA UNIVERSITY: VISAKHAPATNAM
M.Tech
Artificial Intelligence & Machine Learning
Course Structure and Scheme of Valuation w.e.f. 2021-2022

I-SEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.

MTAIML11 Mathematicas for Machine Learning 3 - 70 30 100 3

MTAIML12 Artificial Intelligence 3 - 70 30 100 3

MTAIML13 Elective-I 3 - 70 30 100 3
MTAIML14 Elective-II 3 - 70 30 100 3
MTCST15 Research Methodology &IPR 3 - 70 30 100 2
MTCST16 Organizational Behavior
3 - 70 30 100 0
(Audit Course)
MTAIML17 Artificial Intelligence Lab - 3 50 50 100 2
MTAIML18 Data mining Lab using Python - 3 50 50 100 2
Total 18 6 520 280 800 18

Elective-I: Data Mining/Cloud Computing/Evolutionary Computing

Elective II: Big Data Analytics/Internet of Things/Pattern Recognition

II-SEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIML21 Machine Learning 3 - 70 30 100 3
MTAIML22 Soft Computing 3 - 70 30 100 3
MTAIML23 Elective-III 3 3 - 70 30 100 3
MTAIML24 Elective-IV 3 - 70 30 100 3
MTCST25 Entrepreneurship (Audit Course) 3 - 70 30 100 0
MTAIML26 Machine Learning Lab - 3 50 50 100 2
MTAIML27 Soft Computing Lab - 3 50 50 100 2
MTAIML28 Mini Project With Seminar - 3 - 100 100 2
Total 15 9 450 350 800 18
Elective-III: Computer Vision/Natural Language Processing/Recommender Systems
Elective-IV: Robotics and Intelligent Systems/Reinforcement Learning/NoSQL Databases
 III-SEMESTER

Periods/week Max. Marks

Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIMLR31 Elective-V 3 - 70 30 100 3
MTAIMLR32 Open Elective 3 - 70 30 100 3
MTAIMLR33 Dissertation-I / Industrial project - 100 - 100 10
Total 6 - 240 60 300 16

Elective V : Deep Learning/Expert Systems/High Performance Computing

Open Elective :Business Analytics/Operations Research/Social Media Analytics

IVSEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTCSTAIR41 Dissertation - II - - 100 - 100 16
Total - - 100 - 100 16
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML11 MATHEMATICAL FOR MACHINE LEARNING

Instruction: 3Periods/week Time:3Hours Credits:3

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
• Gain foundation in mathematical concepts related to Linear algebra necessary for ML
• Understands the concepts related to Orthogonality and rotations
• Learns different forms of matrix decompositions
• Understands the concepts of differentiation for finding gradients and curvatures
• Learns various optimization methods
Course Outcomes: At the end of the course, student will be able to
• Attains the capability to solve linear equations and define mappings
• Extract latent orthogonal features from the set of examples using PCA / SVD
• Estimate the gradients of matrices to apply back propagation and other techniques for
parameter update
• Capable of estimating the summary statistics of datasets and select appropriate model to fit the
data

UNIT-I
Linear Algebra: Systems of Linear Equations, Matrices, Solving Systems of Linear Equations,
Vector Spaces, Linear Independence, Basis and Rank, Linear Mappings, Affine Spaces
UNIT-II
Analytic Geometry: Norms, Inner Products, Lengths and Distances, Angles and Orthogonality,
Orthonormal Basis, Orthogonal Complement, Inner Product of Functions, Orthogonal
Projections, Rotations
UNIT-III
Matrix Decompositions: Determinant and Trace, Eigen values and Eigen vectors, Cholesky
Decomposition, Eigen decomposition and Diagonalization, Singular Value Decomposition,
Matrix Approximation, Matrix Phylogeny
UNIT-IV
Vector Calculus : Differentiation of Univariate Functions, Partial Differentiation and Gradients,
Gradients of Vector-Valued Functions, Gradients of Matrices, Useful Identities for Computing
Gradients, Backpropagation and Automatic Differentiation, Higher-Order Derivatives,
Linearization and Multivariate Taylor Series
UNIT-V
Probability and Distributions: Construction of a Probability Space, Discrete and Continuous
Probabilities, Sum Rule, Product Rule, and Bayes’ Theorem, Summary Statistics and
Independence, Gaussian Distribution, Conjugacy and the Exponential Family, Change of
Variables/Inverse Transform
UNIT-VI
Continuous Optimization: Optimization Using Gradient Descent, Constrained Optimization and
Lagrange Multipliers, Convex Optimization
Text Books:
1. “Mathematics for Machine Learning”, Marc Peter Deisenroth, A. Aldo Faisal and Cheng
Soon Ong, Cambridge University Press.
2. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd
Edition, Trevor Hastie, Robert Tibshirani, Jerome Friedman, Springer 2017.

Reference Books:
1. Machine Learning: An Applied Mathematics Introduction, Paul Wilmott, Panda Ohana
Publishing 2019.
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML12 ARTIFICIAL INTELLIGENCE

Instruction: 3Periods/week Time:3Hours Credits:3

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
• Gain a historical perspective of Artificial Intelligence (AI) and its foundations.
• Become familiar with basic principles of AI toward problem solving, inference, perception,
knowledge representation, and learning.
• Investigate applications of AI techniques in intelligent agents, expert systems, artificial neural
networks and other machine learning models.
• Experience AI development tools such as an ‘AI language’, expert system shell, and/or data
mining tool. Experiment with a machine learning model for simulation and analysis.
• Explore the current scope, potential, limitations, and implications of intelligent systems.

Course Outcomes (COs): At the end of the course, student will be able to
• Demonstrate knowledge of the building blocks of AI as presented in terms of intelligent agents.
• Analyze and formalize the problem as a state space, graph, design heuristics and select amongst
different search or game based techniques to solve them.
• Develop intelligent algorithms for constraint satisfaction problems and also design intelligent
systems for Game Playing.
• Attain the capability to represent various real life problem domains using logic based
techniques and use this to perform inference or planning.
• Solve problems with uncertain information using Bayesian approaches.
UNIT-I:
Introduction to artificial intelligence: Introduction, history, intelligent systems, Turing Test,
Role of Knowledge, AI applications, tic-tac-tie game playing, current trends in AI,
Problem solving: state-space search and control strategies: Introduction, general problem
solving, characteristics of problem, AI problem solving as state space search, exhaustive searches,
heuristic search techniques, Hill climbing , A* algorithms,

UNIT-II:
Logic and Theorem Proving concepts: Introduction, propositional calculus, proportional logic,
natural deduction system, axiomatic system, semantic tableau system in proportional logic,
resolution refutation in proportional logic, predicate logic
UNIT-III:
Problem reduction and game playing: Introduction to problem reduction, AO* algorithm,
constraint satisfaction algorithm, Cryptarithmetic Problem solving, Means Ends analysis, game
playing, Min-Max algorithm for game playing, alpha-beta pruning, iterative-deepening, two-
player perfect information games,

UNIT-IV
Representation of Knowledge with Rules: Production System, Forward versus Backward
chaining, Rule Matching and chain control, Non-Monotonic reasoning, Truth maintenance
systems,

UNIT-V:
Uncertain Reasoning: Probability theory: Introduction, probability theory, Bayes theorem,
Bayesian belief networks, certainty factor theory, Dempster-Shafer theory, Statistical Inference
UNIT-VI:
Knowledge representation: Introduction, approaches to knowledge representation, knowledge
representation using semantic network, extended semantic networks for KR, knowledge
representation using frames, advanced knowledge representation techniques: Introduction,
conceptual dependency theory, script structure, cyc theory, case grammars, semantic web.

UNIT-VII:
Planning: Overview, Blocks world as example, components of planning system, Goal stack
planning, Nonlinear planning, Hierarchical planning, Reactive Systems
Expert Systems: Representing and using Domain knowledge, examples of expert systems,
Expert system Architectures, Components, Building an expert system, Expert system shells

Text Books:
1. Artificial intelligence, A modern Approach, 2nded, Stuart Russel, Peter Norvig, Prentice Hall
2. Artificial Intelligence- 3rd Edition, Rich, Kevin Knight, Shiv Shankar B Nair, TMH
3. Introduction To Artificial Intelligence And Expert Systems, 1st Edition, Patterson, Pearson
India, 2015

Reference Books:
1. Artificial intelligence, structures and Strategies for Complex problem solving, 5th Edition,
George F Lugar,PEA
2. Introduction to Artificial Intelligence, Ertel, Wolf Gang, Springer, 2017
3. Artificial Intelligence, SarojKaushik, 1st Edition, CENGAGE Learning, 2011

Detailed Syllabus for M.Tech (AI&ML) First Semester

 MTAIML13 ELECTIVE-I DATA MINING

Instruction: 3Periods/week Time:3Hours Credits:3

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Course Outcomes:
After the completion of the course, student will be able to:
• Compare types of data, quality of data, suitable measures required to perform data analysis.
(UNIT-I)
• Choose appropriate classification technique to perform classification, model building and
evaluation (UNIT-II)
• Make use of association rule mining techniques on categorical and continuous data (UNIT
III)
• Identify and apply clustering algorithm (with open source tools), interpret, evaluate and
report the result (UNIT IV)
• Analyze and Compare anomaly detection techniques (UNI-V)

Unit I:
Introduction to Data mining, types of Data, Data Quality, Data Processing, Measures of Similarity
and Dissimilarity, Exploring Data: Data Set, Summary Statistics, Visualization, OLAP and multi-
dimensional data analysis.

Unit II:
Classification: Basic Concepts, Decision Trees and model evaluation: General approach for
solving a classification problem, Decision Tree induction, Model over fitting: due to presence of
noise, due to lack of representation samples, Evaluating the performance of classifier

Unit III
Nearest Neighborhood classifier, Bayesian Classifier, Support vector Machines: Linear SVM,
Separable and Non Separable case.

Unit IV:
Association Analysis: Problem Definition, Frequent Item-set generation, a priori Algorithm, rule
generation, compact representation of frequent item sets, FP-Growth Algorithms.

Unit-V:
Handling Categorical, Continuous attributes, Concept hierarchy, Multi-dimensional Association
Rules, Sequential pattern mining, Sub graph pattern mining algorithms

Unit VI:
Clustering: Over view, K-means, Agglomerative Hierarchical clustering, DBSCAN, Cluster
evaluation: overview, Unsupervised Cluster Evaluation using cohesion and separation, using
proximity matrix, Scalable Clustering algorithm

Unit VII:
Anomaly Detection: Characteristics of Anomaly Detection Problems and Methods, Statistical
Approaches, Proximity-based Approaches, Clustering-based Approaches and Reconstruction-
based Approaches

Text Books:
1. Introduction to Data Mining: Pang-Ning Tan; Michael Steinbach; AnujKarpatne; Vipin
Kumar, 2nd edition.
2. Data Mining, Concepts and Techniques, 2nd edition, Jiawei Han, MichelineKamber, Elsevier,
2006.
Reference Books:
1. Fundamentals of data warehouses, 2ndedition,Jarke, Lenzerini, Vassiliou, Vassiliadis, Springer.
Suggested NPTEL Course and other Useful Websites:
1. https://nptel.ac.in/courses/106105174/
2. http://cse20-iiith.vlabs.ac.in/
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML13 ELECTIVE-I CLOUD COMPUTING

Instruction: 3Periods/week Time:3Hours Credits:3

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
• To implement Virtualization
• To implement Task Scheduling algorithms.
• Apply Map-Reduce concept to applications.
• To build Private Cloud.
• Broadly educate to know the impact of engineering on legal and societal issues involved.

Course Outcomes: At the end of the course, student will be able to

• Interpret the key dimensions of the challenge of Cloud Computing
• Examine the economics, financial, and technological implications for selecting cloud
computing for own organization.
• Assessing the financial, technological, and organizational capacity of employer’s for actively
initiating and installing cloud-based applications
• Evaluate own organizations’ needs for capacity building and training in cloud computing-
related IT areas.
• Illustrate Virtualization for Data-Center Automation.

UNIT I:
Introduction: Network centric computing, Network centric content, peer-to –peer systems, cloud
computing delivery models and services, Ethical issues, Vulnerabilities, Major challenges for
cloud computing. Parallel and Distributed Systems: Introduction, architecture, distributed
systems, communication protocols, logical clocks, message delivery rules, concurrency, model
concurrency with Petri Nets.

UNIT II:
Cloud Infrastructure: At Amazon, The Google Perspective, Microsoft Windows Azure, Open
Source Software Platforms, Cloud storage diversity, Inter cloud, energy use and ecological
impact, responsibility sharing, user experience, Software licensing,

UNIT-III
Cloud Computing :Applications and Paradigms: Challenges for cloud, existing cloud
applications and new opportunities, architectural styles, workflows, The Zookeeper, The Map
Reduce Program model, HPC on cloud, biological research.

UNIT IV:
Cloud Resource virtualization: Virtualization, layering and virtualization, virtual machine
monitors, virtual machines, virtualization- full and para, performance and security isolation,
hardware support for virtualization, Case Study: Xen, vBlades,
UNIT-V
Cloud Resource Management and Scheduling: Policies and Mechanisms, Applications of
control theory to task scheduling, Stability of a two-level resource allocation architecture,
feedback control based on dynamic thresholds, coordination, resource bundling, scheduling
algorithms, fair queuing, start time fair queuing, cloud scheduling subject to deadlines,
Scheduling Map Reduce applications, Resource management and dynamic application scaling.

UNIT VI:
Storage Systems: Evolution of storage technology, storage models, file systems and database,
distributed file systems, general parallel file systems. Google file system. Apache Hadoop, Big
Table, Megastore (text book 1), Amazon Simple Storage Service(S3) (Text book 2), Cloud
Security: Cloud security risks, security – a top concern for cloud users, privacy and privacy
impact assessment, trust, OS security, Virtual machine security, Security risks.

UNIT VII:
Cloud Application Development: Amazon Web Services : EC2 – instances, connecting clients,
security rules, launching, usage of S3 in Java, Installing Simple Notification Service on Ubuntu
10.04, Installing Hadoop on Eclipse, Cloud based simulation of a Distributed trust algorithm,
Cloud service for adaptive data streaming ( Text Book 1), Google: Google App Engine, Google
Web Toolkit (Text Book 2), Microsoft: Azure Services Platform, Windows live, Exchange
Online, Share Point Services, Microsoft Dynamics CRM (Text Book2).

Text Books:
1. Cloud Computing, Theory and Practice, Dan C Marinescu, MK Elsevier
2. Cloud Computing, A Practical Approach, Anthony T Velte, Toby J Velte, Robert
Elsenpeter,TMH

Reference book:
1. Mastering Cloud Computing, Foundations and Application Programming, Raj Kumar
Buyya, Christen vecctiola, S Tammaraiselvi,TMH
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML13 ELECTIVE-I EVOLUTIONARY COMPUTING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Syllabus:
1. Problems to Be Solved: Optimisation, Modelling, and Simulation Problems, Search Problems,
Optimisation Versus Constraint Satisfaction, The Famous NP Problems.
Evolutionary Computing: The Main Evolutionary Computing Metaphor, The Inspiration from
Biology, Evolutionary Computing: Why?
2. Evolutionary Algorithm: Components of Evolutionary Algorithms, An Evolutionary Cycle by
Hand, Example Applications, The Operation of an Evolutionary Algorithm, Natural Versus
Artificial Evolution, Evolutionary Computing, Global Optimisation, and Other Search
Algorithms.
Representation, Mutation, and Recombination: Representation and the Roles of Variation
Operators, Binary Representation, Integer Representation, Real-Valued or Floating-Point
Representation, Permutation Representation, Tree Representation.
3. Fitness, Selection, and Population Management: Population Management Models, Parent
Selection, Survivor Selection, Selection Pressure, Multimodal Problems, Selection, and the
Need for Diversity.
Popular Evolutionary Algorithm Variants: Genetic Algorithms, Evolution Strategies,
Evolutionary Programming, Genetic Programming, Learning Classifier Systems, Differential
Evolution, Particle Swarm Optimisation, Estimation of Distribution Algorithms.
4. Parameters and Parameter Tuning: Evolutionary Algorithm Parameters, EAs and EA
Instances, Designing Evolutionary Algorithms, The Tuning Problem, Algorithm Quality:
Performance and Robustness, Tuning Methods.
Parameter Control: Introduction, Examples of Changing Parameters, Classification of Control
Techniques, Examples of Varying EA Parameters,
5. Working with Evolutionary Algorithms: What Do You Want an EA to Do?, Performance
Measures, Test Problems for Experimental Comparisons, Example Applications.
Hybridisation with Other Techniques: Memetic Algorithms, Motivation for Hybridising EAs,
Structure of a Memetic Algorithm, Adaptive Memetic Algorithms, Design Issues for Memetic
Algorithms, Example Application: Multistage Memetic Timetabling.
6. Nonstationary and Noisy Function Optimisation: Characterisation of Nonstationary Problems,
The Effect of Different Sources of Uncertainty, Algorithmic Approaches
Multi-objective Evolutionary Algorithms: Multi-objective Optimisation Problems, Dominance
and Pareto Optimality, EA Approaches to Multi-objective Optimisation, Example Application:
Distributed Coevolution of Job Shop Schedules.
7. Constraint Handling: Two Main Types of Constraint Handling, Approaches to Handling
Constraints, Example Application: Graph Three-Colouring
 Interactive Evolutionary Algorithms: Characteristics of Interactive Evolution, Algorithmic
Approaches to the Challenges of IEAs, Interactive Evolution as Design vs. Optimisation,
Example Application: Automatic Elicitation of User Preferences.
Text book:
Introduction to Evolutionary Computing, A.E. Eiben , J.E. Smith, © Springer-Verlag Berlin Heidelberg
2015
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML14 ELECTIVE-II BIG DATA ANALYTICS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
This course is aimed at enabling the students to
• Provide an overview of an exciting growing field of big data analytics.
• Introduce the tools required to manage and analyze big data like Hadoop, NoSQL, Map
Reduce, HIVE, Cassandra, Spark.
• Teach the fundamental techniques and principles in achieving big data analytics with
scalability and streaming capability.
• Optimize business decisions and create competitive advantage with Big Data analytics
Course Outcomes:
After the completion of the course, student will be able to
• Illustrate on big data and its use cases from selected business domains.
• Interpret and summarize on NoSQL, Cassandra
• Analyze the HADOOP and Map Reduce technologies associated with big data analytics and
explore on Big Data applications Using Hive.
• Make use of Apache Spark, RDDs etc. to work with datasets.
• Assess real time processing with Spark Streaming.

UNIT I:
What is big data, why big data, convergence of key trends, unstructured data, industry examples
of big data, web analytics, big data and marketing, fraud and big data, risk and big data, credit
risk management, big data and algorithmic trading, big data and healthcare, big data in medicine,
advertising and big data, big data technologies, introduction to Hadoop, open source technologies,
cloud and big data, mobile business intelligence, Crowd sourcing analytics, inter and trans
firewall analytics.

UNIT II:
Introduction to NoSQL, aggregate data models, aggregates, key-value and document data models,
relationships, graph databases, schema less databases, materialized views, distribution models,
sharding, master-slave replication, peer- peer replication, sharding and replication, consistency,
relaxing consistency, version stamps, Working with Cassandra ,Table creation, loading and
reading data.

UNIT III:
Data formats, analyzing data with Hadoop, scaling out, Architecture of Hadoop distributed file
system (HDFS), fault tolerance ,with data replication, High availability, Data locality , Map
Reduce Architecture, Process flow, Java interface, data flow, Hadoop I/O, data integrity,
compression, serialization.
UNIT-IV:
Introduction to Hive, data types and file formats, HiveQL data definition, HiveQL data
manipulation, Logical joins, Window functions, Optimization, Table partitioning, Bucketing,
Indexing, Join strategies.

UNIT V:
Apache spark- Advantages over Hadoop, lazy evaluation, In memory processing, DAG, Spark
context, Spark Session, RDD, Transformations- Narrow and Wide, Actions, Data frames ,RDD
to Data frames, Catalyst optimizer, Data Frame Transformations, Working with Dates and
Timestamps, Working with Nulls in Data,

UNIT-VI
Working with Complex Types, Working with JSON, Grouping, Window Functions, Joins, Data
Sources, Broadcast Variables, Accumulators, Deploying Spark- On-Premises Cluster
Deployments, Cluster Managers- Standalone Mode, Spark on YARN , Spark Logs, The Spark
UI- Spark UI History Server, Debugging and Spark First Aid

UNIT VII:
Spark-Performance Tuning, Stream Processing Fundamentals, Event-Time and State full
Processing - Event Time, State full Processing, Windows on Event Time- Tumbling Windows,
Handling Late Data with Watermarks, Dropping Duplicates in a Stream, Structured Streaming
Basics - Core Concepts, Structured Streaming in Action, Transformations on Streams, Input and
Output.

Text Books:
1. Big Data, Big Analytics: Emerging, Michael Minnelli, Michelle Chambers, and AmbigaDhiraj
2. SPARK: The Definitive Guide, Bill Chambers &MateiZaharia, O'Reilley, 2018Edition
3. Business Intelligence and Analytic Trends for Today's Businesses", Wiley,2013
4. P. J. Sadalage and M. Fowler, "NoSQL Distilled: A Brief Guide to the Emerging World
Polyglot Persistence", Addison-Wesley Professional,2012
5. Tom White, "Hadoop: The Definitive Guide", Third Edition, O'Reilley,2012

Reference Books:
1. "Hadoop Operations", O'Reilley, Eric Sammer,2012
2. "Programming Hive", O'Reilley, E. Capriolo, D. Wampler, and J. Rutherglen,2012
3. "HBase: The Definitive Guide", O'Reilley, Lars George,2011
4. "Cassandra: The Definitive Guide", O'Reilley, Eben Hewitt,2010
5. "Programming Pig", O'Reilley, Alan Gates,2011
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML14 ELECTIVE-II INTERNET OF THINGS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Course Objectives:
• Vision and Introduction to Internet of Things(IoT).
• Understand IoT Market perspective.
• Data and Knowledge Management and use of Devices in IoT Technology.
• Understand State of the Art – IoT Architecture.
• Understand Real World IoT Design Constraints, Industrial Automation and Commercial.
Course Outcomes (COs): At the end of the course, student will be able to
• Explain in a concise manner how the general Internet as well as Internet of Things work.
• Understand constraints and opportunities of wireless and mobile networks for Internet of
Things.
• Use basic sensing and measurement and tools to determine the real-time performance of
network of devices.
• Develop prototype models for various applications using IoT technology.

UNIT I:
The Internet of Things: An Overview of Internet of things, Internet of Things Technology,
behind IoTs Sources of the IoTs, M2M Communication, Examples of IoTs, Design Principles For
Connected Devices Internet Connectivity Principles, Internet connectivity, Application Layer
Protocols: HTTP, HTTPS, FTP, Telnet.
UNIT II:
Business Models for Business Processes in the Internet of Things ,IoT/M2M systems LAYERS
AND designs standardizations ,Modified OSI Stack for the IoT/M2M Systems ,ETSI M2M
domains and High- level capabilities ,Communication Technologies, Data Enrichment and
Consolidation and Device Management Gateway Ease of designing and affordability
UNIT III:
Design Principles for the Web Connectivity for connected-Devices, Web Communication
protocols for Connected Devices, Message Communication protocols for Connected Devices,
Web Connectivity for connected-Devices.
UNIT IV:
Data Acquiring, Organizing and Analytics in IoT/M2M, Applications /Services /Business
Processes, IOT/M2M Data Acquiring and Storage, Business Models for Business Processes in
the Internet Of Things, Organizing Data, Transactions, Business Processes, Integration and
Enterprise Systems.
UNIT V:
Data Collection, Storage and Computing Using a Cloud Platform for IoT/M2M
Applications/Services, Data Collection, Storage and Computing Using cloud platform Everything
as a service and Cloud Service Models, IOT cloud-based services using the Xively
(Pachube/COSM), Nimbits and other platforms Sensor, Participatory Sensing, Actuator, Radio
Frequency Identification, and Wireless, Sensor Network Technology, Sensors
Technology,Sensing the World.

Text Books:
1. Internet of Things: Architecture, Design Principles And Applications, Rajkamal, McGraw
Hill Higher Education
2. Internet of Things, A.Bahgya and V.Madisetti, Univesity Press,2015
Reference Books:
1. Designing the Internet of Things, Adrian McEwen and Hakim Cassimally,Wiley
Getting Started with the Internet of Things,CunoPfister , Oreilly
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML14 ELECTIVE-II PATTERN RECOGNITION
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives: From the course the student will learn
• Concepts of Algorithms, Searching and Sorting techniques, Trees, Binary trees,
representation, traversal.
• Dictionaries, ADT for List, Stack, Queue, Hash table representation, Hash functions, Priority
queues, Priority queues using heaps, Searchtrees.
• AVL trees, operations of AVL trees, Red- Black trees, Splay trees, comparison of
searchtrees.
Course Outcomes:
After the completion of the course, student will be able to
• Ability to write and analyze algorithms for algorithm correctness and efficiency
• Master a variety of advanced Abstract Data Type (ADT) and data structures and their
Implementation
• Demonstrate various searching, sorting and hash techniques and be able to apply and solve
problems of reallife
• Design and implement variety of data structures including linked lists, binary trees, heaps,
graphs and search trees
• Ability to compare various search trees and find solutions for IT related problems

UNIT I:
Introduction: Overview of Pattern Recognition- Relations of PR with other Systems, PR
Applications, Different Approaches to Pattern Recognition- Statistical Approach to PR, Syntactic
Approach to PR, Neural Approach to PR, Examples of PR Approaches. Other Approaches to PR.

UNIT II:
Structure of PR System: Abstract Representation of PR Mappings, Structure of PR System,
Patterns and Feature s, Feature Extraction Examples, Object Description and Classification,
Figure Recognition, Numerical Results and Analysis. Feature Vector and Feature Space, training
and Learning in PR System.

UNIT III:
Statistical Pattern Recognition: Introduction, Gaussian Case and Class Dependency,
Discriminate Function, Examples, Classifier Performance

UNIT IV:
Training: Parametric Estimation and Supervised Learning, Maximum Likely Hood Estimation,
Bayesian Parameter Estimation Approach , Parzen Windows, Direct Classification Using
Training set., Unsupervised Learning and Clustering, Clustering for Unsupervised Learning and
Classification
UNIT V:
Syntactic Pattern Recognition: Overview of Syntactic Pattern Recognition, Grammar Based
Approaches and Applications, Examples of String Generation as Pattern Description, 2-D line
Drawing Description Grammar, Character Description using PDL, Object Description using
Projected Cylinder Models, Block World Description Models, Heuristic Generation of Grammars

UNIT VI:
Recognition of Syntactic Description: Recognition by Matching, Recognition by Parsing, CYK
Parsing Algorithm, Augmented Transition Nets in Parsing, Graph Based structure representation,
Structured Strategy to Compare Attributed Graphs.

UNIT VII:
Neural Pattern Recognition: Introduction to Neural Networks,, Neural Network Structure for
PR Applications, Physical Neural Networks, ANN Model, NN Based PR Association, Matrix
Approaches and Examples

UNIT VIII:
Feed Forward Neural Networks: Training by Back Propagation, Hope field Approach to Neural
Computing, Other related Neural Approaches and Extensions

Text Book:
1. Pattern Recognition- Statistical, Structural and Neural Approaches, Rober.J. Shelkoff, John
Wiley & Sons, NY1992,ISBN0-471-52974-5

Reference Book:
1. Neural Networks for pattern recognition, Christopher M.Bishop Oxford UniversityPress.
2. Pattern Classification, Richard O.Duda ,Wiley IndiaEdition

Detailed Syllabus for M.Tech (AI&ML) First Semester

MTAIML15 RESEARCH METHODOLOGY AND IPR
 Common for M.Tech (CST, IT, CN&IS, AI&ML)

Instruction: 3Periods/week Time:3Hours Credits:2

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Unit 1: Meaning of research problem, Sources of research problem, Criteria Characteristics of a

good research problem, Errors in selecting a research problem, Scope and objectives of research
problem. Approaches of investigation of solutions for research problem, data collection,
analysis,interpretation, Necessary instrumentations
Unit 2: Effective literature studies approaches, analysis Plagiarism, Research ethics,
Unit 3: Effective technical writing, how to write report, Paper Developing a Research Proposal,
Format of research proposal, a presentation and assessment by a review committee
Unit 4: Nature of Intellectual Property: Patents, Designs, Trade and Copyright. Process of
Patenting and Development: technological research, innovation, patenting, development.
International Scenario: International cooperation on Intellectual Property. Procedure for grants of
patents, Patenting under PCT.
Unit 5: Patent Rights: Scope of Patent Rights. Licensing and transfer of technology. Patent
information and databases. Geographical Indications.
Unit 6: New Developments in IPR: Administration of Patent System. New developments in IPR;
IPR of Biological Systems, Computer Software etc. Traditional knowledge Case Studies, IPR and
IITs.

References:
1. Stuart Melville and Wayne Goddard, “Research methodology: an introduction for
science& engineering students’”
2. Wayne Goddard and Stuart Melville, “Research Methodology: An Introduction”
3. Ranjit Kumar, 2 ndEdition, “Research Methodology: A Step by Step Guide for
beginners”
4. Halbert, “Resisting Intellectual Property”, Taylor & Francis Ltd,2007.
5. Mayall, “Industrial Design”, McGraw Hill, 1992.
6. Niebel, “Product Design”, McGraw Hill, 1974.
7. Asimov, “Introduction to Design”, Prentice Hall, 1962.
8. Robert P. Merges, Peter S. Menell, Mark A. Lemley, “ Intellectual Property in New
Technological Age”, 2016.
9. T. Ramappa, “Intellectual Property Rights Under WTO”, S. Chand, 2008

Detailed Syllabus for M.Tech (AI&ML) First Semester

MTAIML16 ORGANIZATIONAL BEHAVIOR (AUDIT COURSE)
 Common for M.Tech (CST, IT, CN&IS, AI&ML)

Instruction: 3Periods/week Time:3Hours Credits:0

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

UNIT-I Organizational Behavior: Concept of Organization - Concept of Organizational

Behavior - Nature of Organizational Behavior - Role of Organizational behavior - Disciplines
contributing to Organizational Behavior.
UNIT-II Motivation: Definition - Nature of Motivation - Role of Motivation - Theories of
Motivation: Maslow's Need Hierarchy Theory, Herzberg's Motivation Hygiene Theory and
McGregor's Theory X and Theory Y.
UNIT –III Group Dynamics: Meaning - Concept of Group - Types of groups -Formal and
Informal groups - Group development - Group cohesiveness and factors affecting group
cohesiveness.
UNIT-IV Leadership: Concept of Leadership - Difference between Leadership and
Management - Importance of Leadership - Leadership styles: Autocratic leadership, Participative
leadership and Free Rein leadership.
UNIT-V Communication: Meaning - Communication Process - Forms of communication: Oral,
Written and Non- Verbal communication - Direction of communication : Downward, Upward
and Horizontal communication.
UNIT-VI Organizational conflicts: Concept of conflict - Reasons for conflict - Types of
Conflict: Intrapersonal conflict, Interpersonal conflict, Intragroup conflict, Intergroup conflict,
Inter organizational conflict - Conflict management.
UNIT –VII Organizational Change: Nature - Factors in Organizational change -Planned
change: Process of planned change - Resistance to change: Factors in resistance to change -
Overcoming resistance to change.

Text Books:
1.L.M.Prasad: Organizational Behavior, Sultan Chand & Sons, New Delhi -110002
2.K. Aswathappa: Organizational Behavior, Himalaya Publishing House, New Delhi
Reference Books:
1. Stephen Robbins: Organizational Behavior, Pearsons Education, New Delhi.

Detailed Syllabus for M.Tech (AI&ML) First Semester

 MTAIML17 ARTIFICIAL INTELLIGENCE LAB

Instruction: 3Periods/week Time:3Hours Credits:2

Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
● To provide a strong foundation of fundamental concepts in Artificial Intelligence.
● To provide a basic exposition to the goals and methods of Artificial Intelligence.
● To apply the techniques in applications which involve perception, reasoning and learning.
Course Outcomes:
Upon successful completion of the course, the student will be able to:
● Apply the basic principles of AI in problem solving using LISP/PROLOG/ PYTHON
● Implement different state space search algorithms for Game playing using LISP/PROLOG
● Develop an Expert System using JESS/PROLOG

List of Experiments

1. Implementation of DFS for water jug problem using LISP/PROLOG/PYTHON

2. Implementation of BFS for tic-tac-toe problem using LISP/PROLOG/Java
3. Implementation of TSP using heuristic approach using Java/LISP/Prolog
4. Implementation of Simulated Annealing Algorithm using LISP/PROLOG/ PYTHON
5. Implementation of Hill-climbing to solve 8- Puzzle Problem using PYTHON/JAVA
6. Implementation of Monkey Banana Problem using LISP/PROLOG/ PYTHON
7. Implementation of A* Algorithm using LISP/PROLOG/ PYTHON
8. Implementation of AO* Algorithm using LISP/PROLOG/ PYTHON
9. Implementation of Min-Max Game playing algorithm using LISP/PROLOG/ PYTHON
10. Implementation Expert System with forward chaining using JESS/CLIPS
11. Implementation Expert System with backward chaining using RVD/PROLOG
 Detailed Syllabus for M.Tech (AI&ML) First Semester
MTAIML18 DATA MINING LAB USING PYTHON
Instruction: 3Periods/week Time:3Hours Credits:2
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Scope: Lab experiments using R / Python on benchmark datasets

1. Demonstration of pre-processing on some datasets.
2. Demonstration of Data visualization
3. Demonstration of Data dimensionality reduction techniques
4. Demonstration of Classification process using different classifiers
5. Demonstration of Clustering using different clustering methods
6. Demonstration of Association rule extraction using various association algorithms.
 II-SEMESTER
Periods/week Max. Marks
Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIML21 Machine Learning 3 - 70 30 100 3
MTAIML22 Soft Computing 3 - 70 30 100 3
MTAIML23 Elective-III 3 3 - 70 30 100 3
MTAIML24 Elective-IV 3 - 70 30 100 3
MTCST25 Entrepreneurship (Audit Course) 3 - 70 30 100 0
MTAIML26 Machine Learning Lab - 3 50 50 100 2
MTAIML27 Soft Computing Lab - 3 50 50 100 2
MTAIML28 Mini Project With Seminar - 3 - 100 100 2
Total 15 9 450 350 800 18

Elective-III: Computer Vision/Natural Language Processing/Recommender Systems

Elective-IV: Robotics and Intelligent Systems/Reinforcement Learning/NoSQL Databases
 Detailed Syllabus for M.Tech (AI&ML) Second Semester
MTAIML21 MACHINE LEARNING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
Machine Learning course will
• Develop an appreciation for what is involved in learning from data.
• Study a wide variety of learning algorithms.
• Demonstrate how to apply a variety of learning algorithms to data.
• Demonstrate how to perform evaluation of learning algorithms and model selection.
Course Outcomes:
After the completion of the course, student will be able to
• Understand the distribution and diversity of Data
• Extract features useful for building predictive models.
• Gain knowledge on Supervised and unsupervised Learning techniques
• Analyze Statistical learning techniques and Logistic Regression
• Select appropriate Support Vector Machines and Perceptron Algorithm
• Compare the performance of different learning models

UNIT I:
Introduction to Machine Learning, Applications of Machine learning,
Supervisory Learning: Learning classes from examples, Vapnik-Charvonenkis (VC)
Dimension, Probably Approximately Correct(PAC) Learning, noise, learning multiple classes,
regression, model selection and generalization, dimensions of supervised machine learning
algorithms

UNIT II:
Bayesian Decision Theory: Classification, losses and risks, discriminant functions, utility
theory, value of information,
Parametric Methods: Maximum likelihood estimation, evaluating an estimator with bias and
variance, Bayes' estimator, parametric classification, regression, tuning model complexity: bias
vs variance dilemma, model selection procedures

UNIT III:
Multivariate methods: Multivariate data, parameter estimation, missing value imputation,
univariate normal distribution and classification, discrete features, regression, Dimensionality
Reduction: Subset selection, PCA, Factor Analysis, multi-dimensional scaling, LDA

UNIT IV:
Clustering: Mixture densities, K-means clustering, Expectation Maximization algorithm,
mixtures of Latent Variable Models, Supervised learning after clustering, Hierarchical clustering,
choosing number of clusters
UNIT V:
Non-parametric methods: Non-parametric methods density estimation, generalisation to
multivariate data, nonparametric classification, condensed nearest neighbors, non-parametric
regression: smoothing models, choosing smoothing parameters

UNIT VI:
Decision trees and Linear Discrimination: Univariate classification and regression trees, rule
extraction from trees, Multivariate trees,
Generalizing linear model, two class and multi-class geometry of linear discriminant, pairwise
separation, gradient descent, logistic discrimination for binary and multi-class problems,
discrimination by regression, Support vector machines, optimal separating hyperplane, kernel
functions for non-separable spaces, SVM for regression.

UNIT VII:
Hidden Markov Models: Discrete Markov processes, Hidden Markov Models, Three basic
problems of HMM, Evaluation problem, finding the state sequence, Learning model parameters,
continuous observations, Model selection in HMM
Assessing and comparing classification Algorithms: Cross-validation and resampling methods,
measuring error, interval estimation, hypothesis testing

Text Book:
1. Introduction to Machine Learning by Ethem Alpaydin, Prentice-Hall of India, 2006

Reference books:
1. Applied Machine Learning, M.Gopal, McGraw Hill Education, 2019
2. Machine Learning: The art and Science of Algorithms that make sense of Data, Peter Flach,
Cambridge University Press,2012
3. Machine Learning, Tom Mitchell , McGraw Hill, 1997
 Detailed Syllabus for M.Tech (AI&ML) Second Semester
MTAIML22 SOFT COMPUTING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Course Objectives:
• Aims to provide comprehensive understanding of Soft computing approaches for AI problem
solving
• Develops in depth knowledge on concepts related to different types of neural networks
• Provides in depth knowledge on concepts related to Fuzzy logic, membership value assignment
and reasoning with fuzzy quanities
• Helps to understand the development of Fuzzy Inference systems and Fuzzy expert systems
• Introduces the concepts related to Genetic algorithms for learning from examples

Course Outcomes
After completion of course, students would be able to:
• Build neural networks to extract patterns from data
• Build fuzzy inference systems and develop fuzzy expert systems
• Write genetic algorithms for learning the hyper parameters for data classification

UNIT-I:
Introduction to Soft computing, Artificial Neural Network: An Introduction, Evolution of Neural
Networks, Basic Models of Artificial Neural Network, Important Terminologies of ANNs,
McCulloch–Pitts Neuron, Linear Separability, Hebb Network.

UNIT-II:
Supervised Learning Network, Perceptron Networks, Adaptive Linear Neuron (Adaline),
Multiple Adaptive Linear Neurons, Back-Propagation Network, Radial Basis Function Network,
Time Delay Neural Network, Associative Memory Networks, Hopfield Networks

UNIT-III :
Introduction to Fuzzy Logic, Classical Sets and Fuzzy Sets, Classical Relations and Fuzzy
Relations, Tolerance and Equivalence Relations, Noninteractive Fuzzy Sets, Membership
Function, Features of the Membership Functions, Fuzzification, Methods of Membership Value
Assignments, Methods of Membership Value Assignments, Defuzzification

UNIT-IV:
Fuzzy Arithmetic and Fuzzy Measures, Measures of Fuzziness, Fuzzy Rule Base and
Approximate Reasoning, Fuzzy Propositions, Formation of Rules, Decomposition of Rules
(Compound Rules), Aggregation of Fuzzy Rules, Fuzzy Reasoning (Approximate Reasoning),
Fuzzy Inference Systems (FIS), Overview of Fuzzy Expert System

UNTI-V :
Genetic Algorithm, Introduction, Biological Background, Genetic Algorithm and Search Space,
Basic Terminologies in Genetic Algorithm, General Genetic Algorithm, Operators, Stopping
Condition for Genetic Algorithm Flow, Constraints, Problem Solving Using Genetic Algorithm,
The Schema Theorem, Classification of Genetic Algorithm, Advantages and Limitations of
Genetic Algorithm, Applications of Genetic Algorithm.

Text Books:
1. S.N. Sivanandam, S.N. Deepa, Principles of Soft Computing, 3ed, Wiley India.
2. Fakhreddine O. Karray, Clarence W. De Silva, Soft Computing and Intelligent Systems
Design: Theory, Tools and Applications, 1e, Pearson.

References:
1. Fundamentals of Neural Networks – Laurene Fauseett, Prentice Hall India, New Delhi, 1994.
2. Timothy J. Ross,Fuzzy Logic with Engineering Applications, 3 ed, Wiley India
3. E – Neuro Fuzzy and Soft computing – Jang J.S.R., Sun C.T and Mizutami, Prentice hall New
Jersey, 1998
 Detailed Syllabus for M.Tech (AI&ML) Second Semester
MTAIML23 ELECTIVE-III COMPUTER VISION
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objective:
To Recognize and describe both the theoretical and practical aspects of computing with images
and to Connect issues from Computer Vision to Human Vision
Course Outcomes:
• Provide an introduction to computer vision including fundamentals of image formation
• Enumerate the concepts of Feature detection and Matching
• Discuss about Image Segmentation Techniques
• Discuss applications of Feature based alignment like pose estimation
• Discuss different recognition techniques.

UNIT-I
Introduction: What is computer vision, A brief history, Image Formation, Geometric primitives
and transformations, Photometric image formation, The digital camera.

UNIT-II
Feature detection and matching:Points and patches, Feature detectors, Feature descriptors,
Feature matching, Feature tracking, Application: Performance-driven animation, Edges,
Application: Edge editing and enhancement, Lines, Application: Rectangle detection.

UNIT-III
Segmentation: Active contours, Split and merge, Mean shift and mode finding, Normalized
cuts, Graph cuts and energy-based methods, Application: Medical image segmentation.

UNIT-IV
Feature-based alignment: 2D and 3D feature-based alignment, Pose estimation, Geometric
intrinsic calibration, Calibration patterns, Vanishing points, Application: Single view metrology,
Rotational motion, Radial distortion.

UNIT-V
Recognition: Objectdetection,Face detection, Pedestrian detection, Face recognition,Eigenfaces,
Active appearance and 3D shape models, Application: Personal photo collections, Instance
recognition, Category recognition, Context and scene understanding.

Text Books:
1. RichardSzeliski,"ComputerVision:Algorithmsand Applications",Springer,2010.
2. Rafael C. Gonzalez "Digital Image Processing", Pearson Education; Fourth edition (2018)
Reference Books:
1. Forsyth/Ponce,"ComputerVision:AModernApproach",PearsonEducationIndia;2ndedition(2015)
2. S.Nagabhushana,"ComputerVisionandImageProcessing",NewAgeInternationalPvtLtd;First
dition(2005)
 Detailed Syllabus for M.Tech (AI&ML) Second Semester
MTAIML23 ELECTIVE-III NATURAL LANGUAGE PROCESSING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
This course introduces the fundamental concepts and techniques of natural language processing
(NLP).
• Students will gain an in-depth understanding of the computational properties of natural
languages and the commonly used algorithms for processing linguistic information.
• The course examines NLP models and algorithms using both the traditional symbolic and the
more recent statistical approaches.
• Enable students to be capable to describe the application based on natural language processing
and to show the points of syntactic, semantic and pragmatic processing.

Course Outcomes:
After completion of this course
• Demonstrate a given text with basic Language features
• To design an innovative application using NLP components
• Explain a rule based system to tackle morphology/syntax of a language
• To design a tag set to be used for statistical processing for real-time applications
• To compare and contrast the use of different statistical approaches for different types of NLP
applications.

UNIT I:
INTRODUCTION: Origins and challenges of NLP – Language Modeling: Grammar-based LM,
Statistical LM – Regular Expressions, Finite-State Automata – English Morphology, Transducers
for lexicon and rules, Tokenization, Detecting and Correcting Spelling Errors, Minimum Edit
Distance.

UNIT II:
WORD LEVEL ANALYSIS: Unsmoothed N-grams, Evaluating N-grams, Smoothing,
Interpolation and Backoff – Word Classes, Part- of-Speech Tagging, Rule-based, Stochastic and
Transformation-based tagging, Issues in PoS tagging – Hidden Markov and Maximum Entropy
models.

UNIT III:
SYNTACTIC ANALYSIS: Context-Free Grammars, Grammar rules for English, Treebanks,
Normal Forms for grammar – Dependency Grammar – Syntactic Parsing, Ambiguity, Dynamic
Programming parsing – Shallow parsing Probabilistic CFG, Probabilistic CYK, Probabilistic
Lexicalized CFGs – Feature structures, Unification of feature structures

UNIT IV:
SEMANTICS AND PRAGMATICS: Requirements for representation, First-Order Logic,
Description Logics – Syntax-Driven Semantic analysis, Semantic attachments – Word Senses,
Relations between Senses, Thematic Roles, selectional restrictions – Word Sense
Disambiguation, WSD using Supervised, Dictionary & Thesaurus, Bootstrapping methods –
Word Similarity using Thesaurus and Distributional methods.

UNIT V:
DISCOURSE ANALYSIS AND LEXICAL RESOURCES: Discourse segmentation,
Coherence – Reference Phenomena, Anaphora Resolution using Hobbs and Centering Algorithm
– Coreference Resolution – Resources: Porter Stemmer, Lemmatizer, Penn Treebank, Brill’s
Tagger, WordNet, PropBank, FrameNet, Brown Corpus, British National Corpus (BNC).

Text Books:
1. Speech and Language Processing: An Introduction to Natural Language Processing,
nd
Computational Linguistics and Speech, 2 Edition, Daniel Jurafsky, James H. Martin -Pearson
Publication,2014.
2. Natural Language Processing with Python, First Edition, Steven Bird, Ewan Klein and Edward
Loper, OReilly Media,2009.

Reference Books:
st
1. Language Processing with Java and LingPipe Cookbook, 1 Edition, Breck Baldwin, Atlantic
Publisher,2015.
nd
2. Natural Language Processing with Java, 2 Edition, Richard M Reese, OReilly Media,2015.
3. Handbook of Natural Language Processing, Second, NitinIndurkhya and Fred J. Damerau,
Chapman and Hall/CRC Press, 2010.Edition
rd
4. Natural Language Processing and Information Retrieval, 3 Edition, TanveerSiddiqui, U.S.
Tiwary, Oxford University Press,2008.

Detailed Syllabus for M.Tech (AI&ML) Second Semester

 MTAIML23 ELECTIVE-III RECOMMENDER SYSTEMS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Course Objectives:
This course covers the basic concepts of recommender systems, including personalization
algorithms, evaluation tools, and user experiences
Course Outcomes:
• Describe basic concepts behind recommender systems
• Explain a variety of approaches for building recommender systems
• Describe system evaluation methods from both algorithmic and users’ perspectives
• Describe applications of recommender systems in various domains

1. Collabarative recommendations: User-based nearest neighbor recommendation, Item -based

nearest neighbor recommendation, About ratings, Model-based and Preprocessing-based
approaches, Recent practical approaches and Systems.
2. Content- based recommendation: Content representation and content similarity, Similarity-
based retrieval, Other text classification methods.
3. Knoledge-based recommendation: Introduction ,Knowledge representation and reasoning,
Interacting with constraint--based recommenders, Interacting with case-based recommenders,
Example applications.
4. Hybrid recommendation approaches: Opportunities for hybridization , Monolithic
hybridization design, Parallelized hybridization design, Pipelined hybridization design.
5. Evaluating recommender systems: Introduction , General properties of evaluation research,
Popular evaluation designs, Evaluation on historical datasets, Alternate evaluation designs.
6. Attacks on collaborative recommender systems: A first example, Attack dimensions , Attack
types, Evaluation of effectiveness and countermeasures, Countermeasures, Privacy aspects -
distributed collaborative filtering.
7. Online consumer decision making: Introduction , Context effects, Primacy/recency effects,
Further effects, Personality and social psychology. Recommender systems and the next-
generation web: Trust aware recommender systems, Folksonomies and more, Ontological
filtering, Extracting semantics from the web.

Text Book:
1. Recommender Systems: An Introduction by Dietmar Jannach, Markus Zanker, Alexander
Felfernig, Gerhard Friedrich, Cambridge University Press.

Reference Book:
1. Recommender Systems: The Textbook by Charu C. Aggarwal, Springer Publications.

Detailed Syllabus for M.Tech (AI&ML) Second Semester

 MTAIML24 ELECTIVE-IV ROBOTICS AND INTELLIGENT SYSTEMS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objective:
To understand the use of robotics in building intelligent systems.
Course Outcomes:
• Enumerate the fundamentals of robotics and Artificial Inteligence (AI).
• Demonstrate how to setting up a Robot.
• Discuss about the practical Robot Design Process.
• Discuss Object Recognition Using Neural Networks and Supervised Learning

UNIT-I:
Foundation for Advanced Robotics and AI:The basic principle of robotics and AI, What is AI
and what is it not, The example problem, Artificial intelligence and advanced robotics techniques,
Introducing the robot and our development environment, Software components (ROS, Python,
and Linux), Robot control systems and a decision-making framework, The robot control system
– a control loop with soft real-time control

UNIT-II:
Setting Up Your Robot:Technical requirements, What is a robot, Robot anatomy, Subsumption
architecture, Software setup, Hardware, Assembling the tracks,Mounting the tracks, Arm base
assembly, Wiring.

UNIT-III:
A Concept for a Practical Robot Design Process, A systems engineering-based approach to
robotics, Use cases, The problem –put away the toys, Project goals, Decomposing hardware
needs, Breaking down software needs.

UNIT-IV:
Object Recognition Using Neural Networks and Supervised Learning:Technical
requirements, The image recognition process, The image recognition training and deployment
process – step by step, The convolution neural network process, Build the toy/not toy detector

UNIT-V:
Picking up the Toys:Technical requirements, Task analysis, Summary of robot arm learning
process, Teaching the robot arm, Version one – action state reinforcement learning, Adaptive
learning rate, Q-learning implementation,Google’s SAC-X, Amazon Robotics Challenge

Text Books:
1. Francis X. Govers, Artificial Intelligence forRobotics: Build intelligent robots that perform human tasks
usingAI techniques, PACKT
2. J. J. Craig, Introduction to Robotics, Addison Wesley Publishers, 2005
Reference Books:
1. M. Negnevitsky, Artificial Intelligence, A guide to intelligent systems Addison-Wesley, 2005
Detailed Syllabus for M.Tech (AI&ML) Second Semester
 MTAIML24 ELECTIVE-IV REINFORCEMENT LEARNING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objective:
To provide the fundamentals of Reinforcement learning.
Course Outcomes:
• Enumerate the elements of Reinforcement Learning
• Solve the n-armed Bandit problem
• Compare different Finite Markov Decision Process
• Discuss about Monte Carlo Methods in solving real world problems
• List the Applications and Case Studies of Reinforcement Learning

UNIT-I
The Reinforcement Learning Problem: Reinforcement Learning, Examples, Elements of
Reinforcement Learning, Limitations and Scope, An Extended Example: Tic-Tac-Toe, Summary,
History of Reinforcement Learning.
UNIT-II
Multi-arm Bandits: An n-Armed Bandit Problem, Action-Value Methods, Incremental
Implementation, Tracking a Nonstationary Problem, Optimistic Initial Values, Upper-
Confidence-Bound Action Selection, Gradient Bandits, Associative Search (Contextual Bandits)
UNIT-III
Finite Markov Decision Processes: The Agent–Environment Interface, Goals and Rewards,
Returns, Unified Notation for Episodic and Continuing Tasks, The Markov Property, Markov
Decision Processes,
Value Functions, Optimal Value Functions, Optimality and Approximation.
UNIT-IV
Monte Carlo Methods: Monte Carlo Prediction, Monte Carlo Estimation of Action Values,
Monte Carlo Control, Monte Carlo Control without Exploring Starts, Off-policy Prediction via
Importance Sampling, Incremental Implementation, Off-Policy Monte Carlo Control, Importance
Sampling on Truncated Returns
UNIT-V
Applications and Case Studies: TD-Gammon, Samuel’s Checkers Player, TheAcrobot, Elevator
Dispatching, Dynamic Channel Allocation, Job-Shop Scheduling.

Text Books:
1. Richard S. Sutton and Andrew G. Barto, “Reinforcement Learning-An Introduction”,2nd Edition,The
MIT Press,2018
2. Marco Wiering , Martijn van Otterlo Reinforcement Learning: State-of-the-Art (Adaptation,
Learning, and Optimization (12)) 2012th Edition

Reference Books:
1. Vincent François-Lavet , Peter Henderson , Riashat Islam, An Introduction to Deep Reinforcement
Learning (Foundations and Trends(r) in Machine Learning) , 2019

Detailed Syllabus for M.Tech (AI&ML) Second Semester

 MTAIML24 ELECTIVE-IV NoSQL DATABASES
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Outcomes: On completion of this course, the student will be able to
• Enumerate different features of NOSQL Databases
• Compare different data models
• Design a Key-Value Database for a real world problem
• Design a Document Database for a real world problem
• Design a Graph Database for a real world problem

UNIT-I:
Introduction to NoSQL.The Value of Relational Databases, Getting at Persistent Data,
Concurrency, Integration, Standard Model, Impedance Mismatch, Application and Integration
Databases, Attack of the Clusters,The Emergence of NoSQL.
Aggregate Data Models, Aggregates, Consequences of Aggregate Orientation, Key-Value and
Document Data Models, Column-Family Stores, Summarizing Aggregate-Oriented Databases.

UNIT-II :
More Details on Data Models, Relationships, Graph Databases, Schemaless Databases,
Materialized Views, Modeling for Data Access, Distribution Models, Single Server, Sharding,
Master-Slave Replication, Peer-to-Peer Replication, Combining Sharding and Replication,
Consistency, Update Consistency, Read Consistency, Relaxing Consistency, The CAP Theorem,
Relaxing Durability, Quorums

UNIT-III :
Key-Value Databases, Key-Value Store, Key-Value Store Features, Consistency, Transactions,
Query Features, Structure of Data, Scaling, Suitable Use Cases, Storing Session Information, User
Profiles, Preferences, Shopping Cart Data, When Not to Use, Relationships among Data, Multi
operation Transactions, Query by Data, Operations by Sets

UNIT-IV:
Document Databases, Features, Consistency, Transactions, Availability, Query Features,
Scaling, Suitable Use Cases, Event Logging, Content Management Systems, Blogging Platforms,
Web Analytics or Real-Time Analytics, E-Commerce Applications, When Not to Use, Complex
Transactions Spanning Different Operations, Queries against Varying Aggregate Structure

UNIT-V :
Column-Family Stores, Features, Consistency, Transactions, Availability, Query Features,
Scaling, Suitable Use Cases, Event Logging, Content Management Systems, Blogging Platforms,
Counters. Graph Databases, Features, Consistency, Transactions, Availability, Query Features,
Scaling, Suitable Use Cases, Connected Data, Routing, Dispatch, and Location-Based Services
Recommendation Engines
Text Books:
1. Sadalage, P. & Fowler, M., NoSQL Distilled: A Brief Guide to the Emerging World of
Polyglot Persistence. (1st Ed.). Upper Saddle River, NJ: Pearson Education, In, 2012.

Reference Books:
1. Gauravvaish, Getting started with NoSQL , PACKT publishing, ISBN: 978184969488
2. Redmond, E. & Wilson, J., Seven Databases in Seven Weeks: A Guide to Modern Databases
and the NoSQL Movement (1 st Ed.), 2012
3. Raleigh, NC: The Pragmatic Programmers, LLC. ISBN-13: 978- 1934356920 ISBN-10:
1934356921

Detailed Syllabus for M.Tech (AI&ML) Second Semester

MTAIML25 ENTREPRENEURSHIP (AUDIT COURSE)
Instruction: 3Periods/week Time:3Hours Credits:0
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Unit-I
Basic Concepts of Management: Management:-Definition, Nature and Importance; Functions
of the Management; Levels of Management; F.W Taylor's Scientific Management; Henry Fayol's
Principles of Management.

Unit-II
Forms of Business Organizations: Introduction, Types of Business organizations: Private
Sector-Individual Ownership, Partnership, Joint stock companies and Co-Operative
organizations; Public sector-Departmental Organizations, Public Corporations and Government
Companies; The Joint sector Management.

Unit-III
ProductionandoperationsManagement:Plantlocation-Factorstobeconsidered in the selection of
Plant location; Break - even analysis- Significance
andmanagerialapplications;ImportanceofProductionPlanningandControlanditsFunctions;Human
Resource Management and Functions of Human Resource Manager (in brief);Functions of
Marketing; Methods of Raising Finance.

Unit-IV
Entrepreneurship: Definition, Characteristics and Skills ,Types of Entrepreneurs, Entrepreneur
vs. Professional Managers, , Growth of Entrepreneurs, Nature and Importance of Entrepreneurs,
Women Entrepreneurs, Problems of Entrepreneurship.

Unit-V
Entrepreneurial Development and Project Management: Institutions in aid of
Entrepreneurship Development, Idea generation: Sources and Techniques;, Stages in Project
formulation ;Steps for starting a small enterprise -Incentives for Small Scale Industries by
Government.
Text Books:
1. Sharma,S.C,andBanga,T.R.,IndustrialOrganization&EngineeringEconomics,
KhannaPublishers,Delhi,2000.
2. Vasant Desai,The Dynamics of Entrepreneurial Development and Management
(PlanningforfutureSustainablegrowth),HImalayanPublishingHouse,2018.
Reference Books:
1. Aryasri , A.R., Management Science,McGraw HIll Education (India Private Limited ,
NewDelhi2014.
2. Sheela,P.,andJagadeswaraRao,K.,Entrepreneurship,ShreePublishingHouse,Guntur,
Detailed Syllabus for M.Tech (AI&ML) Second Semester
MTAIML26 MACHINE LEARNING LAB
Instruction: 3Periods/week Time:3Hours Credits:2
 Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------

Course Outcomes: On completion of this course, the student will be able to

• Implement machine learning algorithms to real world problems
• Choose appropriate machine learning algorithm for a problem
• Interpret the results of two different machine learning algorithms

List of Experiments:
1. Implement Principal Component Analysis (PCA) on an unsupervised dataset using NumPy.
2. Implement and demonstrate the Singular Value Decomposition (SVD) on a given set of
training data samples. Read the training data from a .CSV file and use NumPy.
3. For a given set of training data examples stored in a .CSV file, implement and demonstrate the
Candidate-Elimination algorithm to output a description of the set of all hypotheses consistent
with the training examples.
4. Write a program to demonstrate the working of the decision tree based ID3 algorithm. Use an
appropriate data set for building the decision tree and apply this knowledge to classify a new
sample.
5. Write a program to implement the naïveBayesian classifier for a sample training data set
stored as a .CSV file. Compute the accuracy of the classifier, considering few test data sets.
6. Assuming a set of documents that need to be classified, use the naïve Bayesian Classifier
model to perform this task. Built-in Java classes/API can be used to write the program. Calculate
the accuracy, precision, and recall for your classifier.
7. Write a program to construct a Bayesian network considering medical data. Use this model
to demonstrate the diagnosis of heart patients using standard Heart Disease Data Set. You can use
Java/Python ML library classes/API.
8. Apply EM algorithm to cluster a set of data stored in a .CSV file. Use the same data set for
clustering using k-Means algorithm. Compare the results of these two algorithms and comment
on the quality of clustering. You can add Java/Python ML library classes/API in the program.
9. Write a program to implement k-Nearest Neighbour algorithm to classify the iris data set.
Print both correct and wrong predictions. Java/Python ML library classes can be used for this
problem.
10. Implement the non-parametric Locally Weighted Regression algorithm in order to fit
data points. Select appropriate data set for your experiment and draw graphs.
11. Create the following plots using Matplotlib, Pandas Visualization, Seaborn on iris dataset,
wine reviews datasets.
a) Scatter Plot
b) Line chart
c) Histogram
d) Heatmap

Text Books:
1. Hands–On Machine Learning with Scikit–Learn and TensorFlow 2e: Concepts, Tools, and
Techniques to Build Intelligent Systems, AurelienGeron, 2019.

References:
 1. https://scikit-learn.org/stable/tutorial/index.html
2. https://archive.ics.uci.edu/ml/index.php
3. https://towardsdatascience.com/pca-and-svd-explained-with-numpy-5d13b0d2a4d8
https://towardsdatascience.com/introduction-to-data-visualization-in-python-89a54c97fbed

Detailed Syllabus for M.Tech (AI&ML) Second Semester

MTAIML27 SOFT COMPUTING LAB
Instruction: 3Periods/week Time:3Hours Credits:2
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Outcomes: On completion of this course, the student will be able to
• Implement neural networks to solve real world problems
• Choose appropriate pre-trained model to solve real time problem
• Parameter tuning using Genetic algorithms
• Implement Fuzzy Inference

Software Packages required:

• Open source tools for building neural network models, fuzzy logic and genetic algorithms

List of Experiments:
1. Build an Artificial Neural Network by implementing the Back propagation algorithm and test
the same using appropriate data sets.
2. Implement multilayer perceptron algorithm for MNIST Hand written Digit Classification.
3. Design a neural network for classifying movie reviews (Binary Classification) using IMDB
dataset.
4. Design a neural Network for classifying news wires (Multi class classification) using Reuters
dataset.
5. Design a neural network for predicting house prices using Boston Housing Price dataset.
6. Implement fuzzy inference for image segmentation.
7. Implement the house price prediction problem with fuzzy reasoning
8. Implement the Fuzzy C-Means algorithm for clustering
9. Implement the basic concepts of genetic algorithms for learning
10. Implement genetic algorithms for hyper parameter tuning in neural networks for classifying
IMDB dataset.

Text Books:
1. Ivan Gridin, “Learning Gentic Algorithms with Python”, BPB publishers, 2021
2. Rajasekaran and Pai, “Neural Networks, Fuzzy Logic and Evolutionary Algorithms:
Synthesis and Applications, PHI, 2017
 III-SEMESTER

Periods/week Max. Marks

Code Name of the subject Total Credits
Theory Lab Ext. Int.
MTAIMLR31 Elective-V 3 - 70 30 100 3
MTAIMLR32 Open Elective 3 - 70 30 100 3
MTAIMLR33 Dissertation-I / Industrial project - 100 - 100 10
Total 6 - 240 60 300 16

Elective V : Deep Learning/Expert Systems/High Performance Computing

Open Elective :Business Analytics/Operations Research/Social Media Analytics

Detailed Syllabus for M.Tech (AI&ML) Third Semester

MTAIML31 ELECTIVE-V DEEP LEARNING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
The objective of this course is to cover the review of ML, fundamentals of feed forward neural
networks, regularization methods and optimization in deep models as well as some advanced
topics such as convolutional neural networks, recurrent neural networks, long short term memory
cells.
Course Outcomes
After completion of course, students would be able to:
• Explore feed forward networks and Deep Neural networks
• Mathematically understand the deep learning approaches and paradigms
• Complex feature extraction with CNN and RNNs
• Apply the deep learning techniques for various applications

1. Machine Learning Basics:

Learning Algorithms, Capacity, Overfitting, and Underfitting, Hyperparameters and Validation
Sets, Estimators, Bias and Variance, Maximum Likelihood Estimation, Bayesian Statistics,
Supervised and Unsupervised Learning algorithms, Stochastic Gradient Descent, Building a ML
algorithm, Challenges and Motivation to Deep learning

2. Deep forward Networks:

Learning XOR, Gradient -based Learning, Hidden Units, Architecture Design, Back-propagation
and other Differentiation algorithms

3. Regularization for Deep Learning:

Parameter Norm Penalties, Norm Penalties as constrained Optimization, Regularization and
under -constrained problems, dataset Augmentation, Noise robustness, semi-supervised learning,
multitask learning, Early stopping, parameter tying and setting, sparse presentations, bagging and
other ensemble methods, dropout

4. Optimization for Training Deep Models:

Difference between learning and pure optimization, Challenges in NN optimization, Basic
algorithms, parameter Initialization strategies, Algorithms with adaptive learning rates,

5. Convolutional Networks:
Convolution operation, Motivation, pooling, convolution and pooling as an infinitely strong prior,
variants of basic convolution function, structured outputs, data types, efficient convolution
algorithms, random or unsupervised features

6. Sequence Modeling: Recurrent and recursive nets:

Unfolding computational graphs, recurrent neural networks, bidirectional RNNs, Encoder-
decoder Sequence-to-sequence Architectures, Deep recurrent networks, recursive neural
networks, challenge of long-term dependencies, echo state networks, leaky units and other
strategies for multiple time scales, Long Short -term Memory (LSTM) and other gated RNNs

7. Practical methodology and applications:

Performance metrics, default baseline models, determining whether to gather more data, selecting
hyperparameters, debugging strategies, multi-digit number recognition, large scale deep learning,
 applications in computer vision and NLP

Text Book:
1. "Deep Learning", Ian Goodfellow, YoshuaBengio and Aaron Courville, published by MIT
Press,UK, 2017 Series
2. Deep Learning with Keras: The Textbook by Antonio Gulli and Sujit Pal, PacktPublishing
Ltd, Birmingham, UK, April 2017

Reference Book:
1. Deep Learning with TensorFlow, The Textbook by Giancarlo Zaccone, Md. Rezaul
Karim, and Ahmed Menshawy, Packt Publishing Ltd, Birmingham, UK, April 2017.

Detailed Syllabus for M.Tech (AI&ML) Third Semester

MTAIML31 ELECTIVE-V EXPERT SYSTEMS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
 1. Introduction: Introduction to Expert System, Definitions, Importance of Expert System,
Characteristic features of Expert System, Applications of Expert System, Different categories of
Expert Systems, Rule Based System Architecture, Neural Network Architecture

2. Knowledge Representations: Components of Knowledge in Expert system, OAV Triplets,

Semantic Networks, Frams Representation via Logic Statements, Production Systems, Clause,
Properties Rule properties, Rule Conversions, Multiple Conclusions, Neural Networks via Rule
Based System

3. Knowledge Acqusition: Introduction Knowledge Acquisition and domain Expert, Selectio of

the domain, Selection of the Knowledge Engineers, Selection of the Expert, Meetings an Plans,
Organization of Meetings, Documentation, Multiple domain Experts, Knowledge Acquisition –
An Example, Knowledge Acquisition using Rule induction, Generating Rules from Trees, ID3
algorithm for Rule Generation

4. Design of Expert System: Introduction, Selecting the appropriate Problem, Stages in the
Developing Expert System, Errors in Development stages, Software Engineering and Expert
Systems, The Expert System Life Cycle, Expert System Design Examples- Certainty factors,
Decision tress

5. Inference Engine: Inference Engine, Insight of Inference Engine, Search Strategies, Forward
Chaining Algorithm, Algorithms for forward Chaining- Baseline Version, Backward Chaining
Algorithm, Algorithms for Back word Chaining-Baseline Version, Mixed Modes of Chaining,
Work sheets for Forward and Back word Chaining.

6. Reasoning Under Uncertainity: Uncertainty, Types of Error, Error and Induction, Classic
Probability, Temporal Reasoning and MorcovChines, TMS, Fuzzy Logic and Natural Languages
computations, Probabilistic Reasoning, probabilistic Networks, Bayesian Networks. Use of
Probability and Fuzzy logic in Expert System, Rule Induction by Machine Learning

7. Software Tools and Architectures: Overview of Expert System Tools, Expert System Shells,
Multiple Paradigm Environments, Abstract architectures, Potential Implementation Problems,
Selecting a Software Tool, Implementation Mechanism of tools, Black Board Architecture,
Reasoning under uncertainty and Truth Maintenance Systems Case-study :A case-study on
Financial planning Expert System, Sale Expert system, DENDRAL andMYCIN

Text Books:
1. Expert System principals and Programming-Giarratano.Rilev.2003
2. Introducion to Expert SystemsV-JamesP.Iginizo.Mc.Graw-Hill.inc
3. Introduction to Expert Systems Peter Jackson, Addison Wesley
Detailed Syllabus for M.Tech (AI&ML) Third Semester
MTAIML31 ELECTIVE-V HIGH PERFORMANCE COMPUTING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course Objectives:
The objective of the subject is to
• Introduce the basic concepts related to HPC architecture and parallel computing
• Discuss various computational techniques for studying soft matter systems.
• Apply these concepts to examine complex biomolecular/materials systems that generally
require large-scale HPC platform with hybrid CPU-GPU architectures

Course Outcomes: After completion of this course

• Design, formulate, solve and implement high performance versions of standard single threaded
algorithms.
• Demonstrate the architectural features in the GPU and MIC hardware accelerators.
• Design programs to extract maximum performance in a multicore, shared memory execution
environment processor.
• Analyze Symmetric and Distributed architectures.
• Develop and deploy large scale parallel programs on tightly coupled parallel systems using the
message passing paradigm.

UNIT I:
Graphics Processing Units-Introduction to Heterogeneous Parallel Computing, GPU
architecture, Thread hierarchy, GPU Memory Hierarchy.

UNIT II:
GPGPU Programming-Vector Addition, Matrix Multiplication algorithms. 1D, 2D, and 3D
Stencil Operations, Image Processing algorithms – Image Blur, Gray scaling. Histogramming,
Convolution, Scan, Reduction techniques.

UNIT III:
Many Integrated Cores-Introduction to Many Integrated Cores. MIC, Xeon Phi architecture.
Thread hierarchy. Memory Hierarchy, .Memory Bandwidth and performance considerations.

UNIT IV:
Shared Memory Parallel Programming- Symmetric and Distributed architectures, OpenMP
Introduction. Thread creation, Parallel regions. Worksharing, Synchronization.

UNIT V:
Message Passing Interface-MPI Introduction, Collective communication, Data grouping for
communication.

Text Books:
1. Programming Massively Parallel Processors A Hands-on Approach, 3e Wen-Mei W Hwu,
David B Kirk, MorgannKaufmann,2013.
2. Using OpenMP, Scientific and Engineering edition, Barbara Chapman, Gabriele Jost, Ruud
vander Pas, MIT Press,2008.
 Reference Books:
1. Intel Xeon Phi Coprocessor Architecture and Tools, RezaurRahman, Apress Open,2013.
2. Using MPI, Gropp, Lusk, Skjellum, The MIT press,2014.
3. High Performance Computing: Programming and Applications, John Levesque, CRC Press,
2010.

Detailed Syllabus for M.Tech (AI&ML) Third Semester

MTAIML32 OPEN ELECTIVE HIGH PERFORMANCE COMPUTING
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
Course objectives
1. to introduce students to problem solving with Business Analytics and the use of spreadsheets
for descriptive analytics, data queries and visualization
2. to introduce students to statistical sampling, sampling distributions, confidence intervals and
statistical inference
3. To familiarize students with various types of regression including simple linear regression and
multiple linear regression
4. To introduce students to key concepts in statistical forecasting models for time series data
5. To familiarize students with predictive decision modeling, model analysis and developing
spreadsheet applications including building linear optimization models on spreadsheets.

Course outcomes
After completion of the course the student should be able to:
1. Describe data and models used for Business Analytics and apply various descriptive analytic
techniques to analyze data
2. Estimating population parameters, interval estimates, construct confidence intervals and
perform hypothesis testing
3. Estimate and interpret the parameters of simple linear regression and multiple lineaR
regressions
4. Apply forecasting models for various time series data including stationary time series, time
series with linear trend and time series with seasonality

Syllabus:
1. Foundations of Business Analytics: Evolution of Business Analytics, Scope, data and models
for Business Analytics, problem solving with Business Analytics, Analytics on spreadsheets,
Excel functions for Database queries, Add-ons for Business Analytics. Descriptive Analytics:
Data visualization, creating charts in MS Excel, Data Queries, Tables, sorting and filtering, Data
summarization with statistics, Data exploration using Pivot tables

2. Statistical Sampling: methods, estimating population parameters, sampling error, sampling

distributions, interval estimates, confidence intervals, using confidence intervals for decision
making, prediction intervals Statistical Inference: Hypothesis testing, one-sample Hypothesis
testing, two-tailed test of Hypothesis for mean, two-sample Hypothesis testing, Analysis of
variance, chi-square test for independence

3. Trendiness and Regression: Modeling Relationships and trends in data, Simple linear
regression, least squares regression, regression on analysis of variance, testing hypothesis for
regression coefficients, Confidence intervals for regression coefficients, Residual analysis and
regression assumptions, Multiple linear regression, building regression models, regression with
categorical independent variables with two or more levels, regression with nonlinear terms,
advanced techniques for regression modeling

4. Forecasting Techniques: Qualitative and judgmental forecasting, statistical forecasting

models, forecasting models for stationery time series, forecasting models for time series with
linear trend, forecasting models for time series with seasonality, selecting appropriate time-series-
 based forecasting models, regression forecasting with casual variables, practice of forecasting

5. Spreadsheet modeling and Analysis: Strategies for predictive decision modelling,

Implementing models on spreadsheet, spreadsheet applications in Business analytics, Model
assumptions, complexity and realism, developing user-friendly applications, analyzing
uncertainty and model assumptions, model analysis using analytics solver platform

6. Linear Optimization & amp; Applications: Building Linear Optimization Models on

spreadsheets, solving Linear Optimization models, Graphical interpretation of linear
optimization, Using optimization models of prediction and insight, Types of constraints in
optimization models, process selection models,
Blending Models, Portfolio Investment models

Text Book
1. “Business Analytics: Methods, Models, and Decisions” James R. Evans, Pearson Publications,
Second edition
Reference Book
1. “Business Analytics: The Science of Data-Driven Decision Making”, U.Dinesh Kumar, Wiley
Publications

Detailed Syllabus for M.Tech (AI&ML) Third Semester

MTAIML32 OPEN ELECTIVE OPERATIONS RESEARCH
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
 UNIT I: Overview of Operations Research, Types of OR Models , Phases of Operations
Research– OR Techniques, Introduction to Linear Programming, Formulation of Linear
Programming Problem, Graphical Solution; Graphical Sensitivity Analysis
UNIT II: Standard Form of LPP, Basic Feasible Solutions , Unrestricted Variables, Simplex
Algorithm , Artificial Variables, Big M Me th od , Two Phase Simplex Method, Degeneracy,
Alternative Optimal, Unbounded Solutions, Infeasible Solutions, Primal And Dual Problems And
Their Relations, Dual Simplex Method
UNIT III: Transportation Problem as LPP, Initial Solutions, North West Corner Rule, Lowest
Cost Method, Vogels Approximation Method, Optimum Solutions of TPP, Degeneracy in
Transportation, Transportation Algorithms
UNIT IV: Assignment Problem , Assignment Problem as LPP, Hungarian Method, Travelling
Salesman Problem, Solutions Of TSP, Sequencing Problems, N-Jobs Two Machine Problems, N-
Jobs K Machines Problems, Two-Jobs M- Machine Problems, Crew Scheduling Problems
UNITV: Network Representation of A Project, CPM and PERT , Critical Path Calculations, Time
– Cost Optimizations, PERT Analysis and Probability Considerations, Resource Analysis in
Network Scheduling.
UNIT VI: Replacement Problems-Individual And Group Replacement Policy, Reliability &
System Failure Problems, Inventory-Factors Effecting Inventory-EOQ, Inventory Problems With
and Without Shortages, Inventory Problems With Price Breakups, Multi Item Deterministic
Problems. Probabilistic Inventory Problems
UNIT VII: Game Theory : Two Person Zero Sum Games , Mixed Strategy Games and Their
Algorithms.

Text Books:
1. Operations Research, KantiSwaroop, P.K. Gupta, Man Mohan, Sulthan Chand& Sons
Education
2. Operations Research–An Introduction, HandyATaha–PearsonEducation.

Detailed Syllabus for M.Tech (AI&ML) Third Semester

MTAIML32 OPEN ELECTIVE SOCIAL MEDIA ANALYTICS
Instruction: 3Periods/week Time:3Hours Credits:3
Internal: 30Marks External:70Marks Total: 100Marks
-------------------------------------------------------------------------------------------------------------
1. Introduction: Analyzing social web, tools used, Basics of network structure, representing
social networks, different network structures and properties, describing nodes and edges with
centrality, describing networks, degree distribution, density, connectivity, centralization

2. Network Visualization: graph layoutgrid layout, visualizating network features, scale issues
Tie strength: measuring tie strength, tie strength and network structure, tie strength and
network propagation

3. Trust: defining trust, naunces of trust, measuring trust, trust in social media, inferring trust,
network-based inference, and similarity based trust inference
Understanding Structure through user attributes and behavior: Analyzing attributes and
behavior, analyzing content, identifying user roles

4. Building Networks: Modeling networks, Sampling methods, egocentric network analysis

Entity Resolution and Link Prediction: Link prediction, Entity resolution, Incorporating
network data, case study for link prediction and entity resolution

5. Propagation in Networks: Epidemic models, Threshold models, firefighter problem,

stochastic models, applications of epidemic models to social media
Community-Maintained Resources: Supporting technologies for community- maintained
resources, Wikies, message boards, repositories, user motivations

6. Location-based Social Interaction: Location technology, mobile location sharing, location-

based social media analysis, privacy and location -based social media
Social Information Filtering: Social sharing and social filtering, automated recommender
systems, case study of trusty based movie recommendations

7. Social Media in Public Sector: Analyzing public-sector social media, case studies of
congressional use of twitter, predicting elections and astroturfing
Privacy: Privacy policies and settings, aggregation and data mining, deanonymization,
inferring data, data ownership and maintaining privacy online, respecting privacy in social
media analysis

Text Book:
1. "Analyzing the Social Web", Jennifer Golbeck Morgan Kaufmann publishers, 2013