R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

SEMESTER – I

S. No. Course Course Name Category Hours per week Credits

codes L T P
1. 21DBS102 Mathematical and Statistical Foundations PC 3 0 0 3
2. 21D97101 Artificial Intelligence PC 3 0 0 3
Program Elective Course - I
3. 21D58103a Machine Learning
21D08102c Cloud Computing PE 3 0 0 3
21D97102a Neural Networks and Genetic Algorithms
Program Elective Course – II PE 3 0 0 3
21D97105 Principles of Data Science
4. 21D25102b Information Retrieval
21D58101 Advanced Data Structures And Algorithms
5. 21D97103 R Programming Lab PC 0 0 4 2
6. 21D97104 Artificial Intelligence Lab PC 0 0 4 2
7. 21DRM101 Research Methodology and IPR MC 2 0 0 2
Audit Course – I
8. 21DAC101a English for Research paper writing AC 2 0 0 0
21DAC101b Disaster Management
21DAC101c Sanskrit for Technical Knowledge
Total 18

1
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

SEMESTER – II

S.No. Course Course Name Category Hours per Credits

codes L week
T P
1. 21D97201 Advanced Data Mining PC 3 0 0 3
2. 21D58203a Deep Learning PC 3 0 0 3
Program Elective Course – III PE 3 0 0 3
3. 21D58301c Data Analytics
21D97203a Pattern Recognition
21D97203b Intelligent Agent Systems
Program Elective Course – IV PE 3 0 0 3
4. 21D97204a Intrusion Detection Systems
21D58203c Computer Vision
21D97204b Natural Language Processing
5. 21D97205 Advanced Data Mining Lab PC 0 0 4 2
6. 21D97206 Deep Learning Lab PC 0 0 4 2
7. 21D97207 Technical seminar PR 0 0 4 2
Audit Course – II AC 2 0 0 0
21DAC201a Pedagogy Studies
8. 21DAC201b Stress Management for Yoga
21DAC201c Personality Development through Life Enlightenment
Skills
Total 18

2
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

SEMSTER - III

S.No. Course Course Name Category Hours per week Credits

codes L T P
1. Program Elective Course –V PE 3 0 0 3
21D97301a Reinforcement Learning
21D97301b Game Theory
21D97301c Applied Artificial Intelligence
2. Open Elective OE 3 0 0 3
21DOE301b Industrial Safety
21DOE301c Business Analytics
21DOE301f Optimization Techniques
3. 21D97302 Dissertation Phase – I PR 0 0 20 10
4. 21D97303 Co-curricular Activities 2
Total 18

SEMESTER - IV

S.No. Course Course Name Category Hours per week Credits

codes L T P
1. 21D97401 Dissertation Phase – II PR 0 0 32 16
Total 16

3
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code MATHEMATICAL AND STATISTICAL FOUNDATIONS L T P C

21DBS102 3 0 0 3
Semester I
Course Objectives:
 To identify the mathematical concepts in the field of data science
 To employ the techniques and methods related to the area of data science in variety of
applications
 To apply logical thinking to understand and solve the problem in context.
Course Outcomes (CO):
 Ability to use the mathematical concepts in the field of data science
 Employ the techniques and methods related to the area of data science in variety of
applications
 Apply logical thinking to understand and solve the problem in context.
UNIT - I Lecture Hrs:8
Basics of Data Science: Introduction; Typology of problems; Importance of linear algebra, statistics
and optimization from a data science perspective; Structured thinking for solving data science
problems
UNIT - II Lecture Hrs:8
Linear Algebra: Matrices and their properties (determinants, traces, rank, nullity, etc.); Eigenvalues
and eigenvectors; Matrix factorizations; Inner products; Distance measures; Projections; Notion of
hyperplanes; half-planes.
UNIT - III Lecture Hrs:9
Probability, Statistics and Random Processes: Probability theory and axioms; Random variables;
Probability distributions and density functions (univariate and multivariate); Expectations and
moments;
UNIT - IV Lecture Hrs:9
Covariance and correlation; Statistics and sampling distributions; Hypothesis testing of means,
proportions, variances and correlations; Confidence (statistical) intervals; Correlation functions;
White-noise process.
UNIT - V Lecture Hrs:9
Optimization: Unconstrained optimization; Necessary and sufficiency conditions for optima;
Gradient descent methods; Constrained optimization, KKT conditions; Introduction to nongradient
techniques; Introduction to least squares optimization; Optimization view of machine learning.
Introduction to Data Science Methods: Linear regression as an exemplar function approximation
problem; Linear classification problems.
Textbooks:
1 G. Strang . Introduction to Linear Algebra, Wellesley-Cambridge Press, Fifth edition, USA, 2016.
2. Bendat, J. S. and A. G. Piersol. Random Data: Analysis and Measurement Procedures. 4th Edition.
John Wiley & Sons, Inc., NY, USA, 2010
Reference Books:
1. Montgomery, D. C. and G. C. Runger. Applied Statistics and Probability for Engineers. 5th
Edition. John Wiley & Sons, Inc., NY, USA, 2011.
2. David G. Luenberger . Optimization by Vector Space Methods, John Wiley & Sons (NY),
1969.
3. Cathy O’Neil and Rachel Schutt . Doing Data Science, O’Reilly Media, 2013.

4
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code ARTIFICIAL INTELLIGENCE L T P C

21D97101 3 0 0 3
Semester I

Course Objectives:
 The goal of Artificial Intelligence is to build software systems that behave "intelligently".
 The ability to create representations of the domain of interest and reason with these
representations is a key to intelligence.
Course Outcomes (CO): Student will be able to
 Understand the major areas and challenges of AI
 Ability to apply basic AI algorithms to solve problems
 Able to describe search strategies and solve problems by applying a suitable search method.
 Able to describe and apply knowledge representation
 To learn different knowledge representation techniques
 Represent knowledge of a domain formally,
 7. Design, implement and apply a knowledge-based system.
UNIT - I Lecture Hrs:9
Introduction: AI problems, foundation of AI and history of AI intelligent agents: Agents and
Environments, the concept of rationality, the nature of environments, structure of agents, problem
solving agents, problem formulation.
UNIT - II Lecture Hrs:9
Searching: Searching for solutions, uniformed search strategies – Breadth first search, depth first
Search. Search with partial information (Heuristic search) Greedy best first search, A* search Game
Playing: Adversial search, Games, minimax, algorithm, optimal decisions in multiplayer games,
Alpha-Beta pruning, Evaluation functions, cutting of search.
UNIT - III Lecture Hrs:9
Knowledge Representation: Using Predicate logic, representing facts in logic, functions and
predicates, Conversion to clause form, Resolution in propositional logic, Resolution in predicate
logic, Unification.
Representing Knowledge Using Rules: Procedural Versus Declarative knowledge, Logic
Programming, Forward versus Backward Reasoning.
UNIT - IV Lecture Hrs:9
Learning: What is learning, Rote learning, Learning by Taking Advice, Learning in Problem-solving,
Learning from example: induction, Explanation-based learning.
Connectionist Models: Hopfield Networks, Learning in Neural Networks, Applications of Neural
Networks, Recurrent Networks. Connectionist AI and Symbolic AI
UNIT - V Lecture Hrs:9
Expert System: Representing and using Domain Knowledge, Reasoning with knowledge, Expert
System Shells, Support for explanation examples, Knowledge acquisition-examples.
Textbooks:
1. Artificial Intelligence – A Modern Approach. Second Edition, Stuart Russel, Peter Norvig,
PHI/ Pearson Education.
2. Artificial Intelligence, Kevin Knight, Elaine Rich, B. Shivashankar Nair, 3rd Edition,2008
3. Artificial Neural Networks B. Yagna Narayana, PHI
Reference Books:
1. Artificial Intelligence, 2nd Edition, E.Rich and K.Knight (TMH).
2. Artificial Intelligence and Expert Systems – Patterson PHI.
3. Expert Systems: Principles and Programming- Fourth Edn, Giarrantana/ Riley, Thomson.
4. PROLOG Programming for Artificial Intelligence. Ivan Bratka- Third Edition – Pearson
5
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
Education.
5. Neural Networks Simon Haykin PHI
6. Artificial Intelligence, 3rd Edition, Patrick Henry Winston., Pearson Edition

6
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code MACHINE LEARNING L T P C

21D58103a (Common to M.Tech CSE, SE,AI & ML) 3 0 0 3
Semester I

Course Objectives:
• To understand various key paradigms for machine learning approaches.
• To familiarize with the mathematical and statistical techniques used in machine learning.
• To understand and differentiate among various machine learning techniques.
Course Outcomes (CO): Student will be able to
• To formulate a machine learning problem
• Select an appropriate pattern analysis tool for analysing data in a given feature space.
• Apply pattern recognition and machine learning techniques such as classification and feature selection
to practical applications and detect patterns in the data.
UNIT - I Lecture Hrs:
Introduction: Definitions, Datasets for Machine Learning, Different Paradigms of Machine Learning, Data
Normalization, Hypothesis Evaluation, VC-Dimensions and Distribution, Bias-Variance Tradeoff,
Regression
UNIT - II Lecture Hrs:
Bayes Decision Theory: Bayes decision rule, Minimum error rate classification, Normal density and
discriminant functions.
Parameter Estimation: Maximum Likelihood and Bayesian Parameter Estimation
UNIT - III Lecture Hrs:
Discriminative Methods: Distance-based methods, Linear Discriminant Functions, Decision Tree, Random
Decision Forest and Boosting
Feature Selection and Dimensionality Reduction: PCA, LDA, ICA, SFFS, SBFS
UNIT - IV Lecture Hrs:
Learning from unclassified data. Clustering. Hierarchical Agglomerative Clustering. k-means partitional
clustering. Expectation maximization (EM) for soft clustering. Semi-supervised learning with EM using
labelled and unlabelled data.
UNIT - V Lecture Hrs:
Kernel Machines: Kernel Tricks, SVMs (primal and dual forms), K-SVR, K-PCA (6 Lectures) Artificial
Neural Networks: MLP, Backprop, and RBF-Net
Textbooks:
1. Shalev-Shwartz,S., Ben-David,S., (2014), Understanding Machine Learning: From Theory to
Algorithms, Cambridge University Press
2. R. O. Duda, P. E. Hart, D. G. Stork (2000), Pattern Classification, Wiley-Blackwell, 2nd Edition.
Reference Books:
1. Machine Learning Methods in the Environmental Sciences, Neural Networks, William W Hsieh,
Cambridge Univ Press.
2. Richard o. Duda, Peter E. Hart and David G. Stork, pattern classification, John Wiley & Sons
Inc.,2001
3. Chris Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995

7
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code CLOUD COMPUTING L T P C

21D08102c (Common to M.Tech CN, SE, AI&ML) 3 0 0 3
Semester I

Course Objectives:
• Understand the hardware, software concepts and architecture of cloud computing
• Realize the importance of Cloud Virtualization, Abstractions and Enabling Technologies.
• Explore the Programming for Applications on Cloud.
• Apply Map-Reduce concept to applications.
Course Outcomes (CO): Student will be able to
• Explain industry relevance of cloud computing and its intricacies, in terms of various
challenges, vulnerabilities, SLAs, virtualization, resource management and scheduling, etc.
• Examine some of the application paradigms, and Illustrate security aspects for building cloud-
based applications.
• Conduct a research study pertaining to various issues of cloud computing.
• Demonstrate the working of VM and VMM on any cloud platforms (public/private), and run a
software service on that.
UNIT - I Lecture Hrs:9
Introduction, Cloud Infrastructure
Cloud computing, Cloud computing delivery models and services, Ethical issues, Cloud vulnerabilities,
Major challenges faced by cloud computing; Cloud Infrastructure: Cloud computing at Amazon, Cloud
computing the Google perspective, Microsoft Windows Azure and online services, Open-source
software platforms for private clouds, Cloud storage diversity and vendor lock-in, Service- and
compliance-level agreements, User experience and software licensing. Exercises and problems
UNIT - II Lecture Hrs:9
Cloud Computing: Application Paradigms
Challenges of cloud computing, Existing Cloud Applications and New Application Opportunities,
Workflows: coordination of multiple activities, Coordination based on a state machine model: The
ZooKeeper, The MapReduce Programming model, A case study: The Grep TheWeb application, HPC
on cloud, Biology research
UNIT - III Lecture Hrs:9
Cloud Resource Virtualization.
Virtualization, Layering and virtualization, Virtual machine monitors, Virtual Machines, Performance
and Security Isolation, Full virtualization and para virtualization, Hardware support for virtualization,
Case Study: Xen a VMM based para virtualization, Optimization of network virtualization, The darker
side of virtualization, Exercises and problems.
UNIT - IV Lecture Hrs:10
Cloud Resource Management and Scheduling
Policies and mechanisms for resource management, Application of control theory to task scheduling on
a cloud, Stability of a two-level resource allocation architecture, Feedback control based on dynamic
thresholds, Coordination of specialized autonomic performance managers; Scheduling algorithms for
computing clouds, Fair queuing, Start-time fair queuing, Borrowed virtual time, Exercises and
problems.
UNIT - V Lecture Hrs:10
Cloud Security, Cloud Application Development
Cloud security risks, Security: The top concern for cloud users, Privacy and privacy impact
assessment, Trust, Operating system security, Virtual machine Security, Security of virtualization,
Security risks posed by shared images, Security risks posed by a management OS, A trusted virtual
machine monitor, Amazon web services, Cloud-based simulation of a distributed trust algorithm, A
trust management service, A cloud service for adaptive data streaming, Exercises and problems.

8
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Amazon Simple Notification services.

Textbooks:
1.Cloud Computing Theory and Practice. Dan C Marinescu: Elsevier (MK), 1st Edition, 2013, ISBN:
9780124046276.
2.Distributed Computing and Cloud Computing, from parallel processing to internet of things. Kai
Hwang, GeofferyC.Fox, Jack J Dongarra: Elsevier(MK), 1st Edition, 2012, ISBN: 978-0-12-385880-1
Reference Books:
1.Cloud Computing Principles and Paradigms, RajkumarBuyya, James Broberg, AndrzejGoscinski:
Willey, 1st Edition, 2014, ISBN: 978-0-470-88799-8.
2.Cloud Computing Implementation, Management and Security, John W Rittinghouse, James F
Ransome: CRC Press, 1st Edition, 2013, ISBN: 978-1-4398-0680-7
Online Learning Resources:
OLI Course: http://oli.cmu.edu (accessed through https://blackboard.andrew.cmu.edu)
The Project Zone:https://TheProject.Zone
Piazza: http://piazza.com/cmu/spring2016/1531915619/home

9
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code NEURAL NETWORKS AND GENETIC ALGORITHMS L T P C

21D97102a 3 0 0 3
Semester I
https://cse.iitkgp.ac.in/~dsamanta/courses/sca/index.html
Course Objectives:
• Neural networks provide a model of computation drastically different from traditional
computers.
• Typically, neural networks are not explicitly programmed to perform a given task; rather,
they learn to do the task from examples of desired input/output behavior.
• To understand the search methods in the genetic algorithms.
• To implement the reproduction concepts.
• To design the techniques of dominance in genetic algorithms
Course Outcomes (CO): Student will be able to
• An ability to understand and the fundamental concepts of Genetic algorithms.
• Understand the consequence of applying various genetic operators.
• Ability to analyze GA operators and implement them to solve different types of GA
problems.
• Creating and understanding about the way the GA is used and the domain of application
UNIT – I Lecture Hrs:9
Characteristics of Neural Networks, Historical Development of Neural Networks Principles,
Artificial Neural Networks: Terminology, Models of Neuron, Topology, Basic Learning Laws,
Pattern Recognition Problem, Basic Functional Units, Pattern Recognition Tasks by the Functional
Units. Feed forward Neural Networks: Introduction, Analysis of pattern Association Networks,
Analysis of Pattern Classification Networks, Analysis of pattern storage Networks; Analysis of
Pattern Mapping Networks
UNIT – II Lecture Hrs:9
Feedback Neural Networks: Introduction, Analysis of Linear Auto associative FF Networks,
Analysis of Pattern Storage Networks. Competitive Learning Neural Networks & Complex pattern
Recognition:
Introduction, Analysis of Pattern Clustering Networks, Analysis of Feature Mapping Networks, and
Associative Memory
UNIT – III Lecture Hrs:9
Introduction to Genetic Algorithm – Robustness of Traditional Optimization and Search methods –
Goals of optimization-GA versus Traditional methods – Simple GA – GA at work – Similarity
templates (Schemata) – Learning the lingo - Mathematical foundations: The fundamental theorem -
Schema processing at work. – The 2-armed & k-armed Bandit problem. – The building Block
Hypothesis. – Minimal deceptive problem.
UNIT – IV Lecture Hrs:9
GA OPERATORS Data structures – Reproduction- Roulette-wheel Selection – Boltzman Selection
– Tournament Selection-Rank Selection – Steady –state selection –Crossover mutation – A time to
reproduce, a time to cross. – Get with the Main program. – How well does it work. – Mapping
objective functions to fitness forum. – Fitness scaling. Coding – A Multi parameter, Mapped, Fixed –
point coding – Discretization – constraints
UNIT - V Lecture Hrs:9
APPLICATIONS OF GA The rise of GA – GA application of Historical Interaction. – Dejung&
Function optimization – Current applications of GA -Advanced operators & techniques in genetic
search :Dominance, Diploidy & abeyance – Inversion & other reordering operators. – other mine-
operators – Niche & Speciation – Multi objective optimization – Knowledge-Based Techniques. –
10
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

GA & parallel processes – Real life problem

Textbooks:
1. Artificial Neural Networks B. Yagna Narayana, PHI
2. Neural Networks Simon Haykin PHI
3. David E. Gold Berg, “Genetic Algorithms in Search, Optimization & Machine Learning”,
Pearson Education, 2001 .
4. S.Rajasekaran, G.A.VijayalakshmiPai, “ Neural Networks, Fuzzy Logic and Genetic
Algorithms “, PHI , 2003 ( Chapters 8 and 9 )
Reference Books:
1. Kalyanmoy Deb, “Optimization for Engineering Design, algorithms and examples”, PHI
1995.
2. An Introduction to Genetic Algorithm by Melanie Mitchell.
3. The Simple Genetic Algorithm Foundation &Theores by Michael P. Vosk

11
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code PRINCIPLES OF DATA SCIENCE L T P C

21D97105 3 0 0 3
Semester I

Course Objectives:
• Discussion and dissemination of best practice in use of data science
• 2 Aims to bring to together researchers interested in data science to focus on techniques and
methods that cut across all disciplines.
• DSC will bring together researchers that develop methods and techniques and those that
apply these methods to their research.
• Will be used to raise awareness of funding opportunities (nationally and internationally) and
potential collaborations related to the use of data analytics/big data techniques.
• Will be led by a small academic steering group to ensure alignment with current academic
topics.
Course Outcomes (CO): Student will be able to
• Use R to carry out basic statistical modeling and analysis.
• Explain the significance of exploratory data analysis (EDA) in data science. Apply basic tools
(plots, graphs, summary statistics) to carry out EDA.
• Describe the Data Science Process and how its components interact.
• Use APIs and other tools to scrap the Web and collect data.
• Apply EDA and the Data Science process in a case study.
UNIT - I Lecture Hrs:8
Introduction: What is Data Science: Big Data and Data Science hype – and getting past the hype,
Why now? – Deification, Current landscape of perspectives, Skill sets needed.
UNIT - II Lecture Hrs:8
Exploratory Data Analysis and the Data Science Process: Basic tools (plots, graphs and summary
statistics) of EDA, Philosophy of EDA, The Data Science Process, Case Study: Real Direct (online
real estate firm).
Three Basic Machine Learning Algorithms: Linear Regression, k-Nearest Neighbours (kNN),k-
means.
UNIT - III Lecture Hrs:9
One More Machine Learning Algorithm and Usage in Applications: Motivating application:
Filtering Spam, Why Linear Regression and k-NN are poor choices for Filtering Spam, Naive Bayes
and why it works for Filtering Spam, Data Wrangling: APIs and other tools for scrapping the Web
Feature Generation and Feature Selection (Extracting Meaning From Data) :Motivating
application: user (customer) retention, Feature Generation (brainstorming, role of domain expertise,
and place for imagination),Feature Selection algorithms, Filters; Wrappers; Decision Trees; Random
Forests.
UNIT - IV Lecture Hrs:9
Recommendation Systems: Building a User-Facing Data Product: Algorithmic ingredients of a
Recommendation Engine, Dimensionality Reduction, Singular Value Decomposition, Principal
Component Analysis.
Mining Social-Network Graphs: Social networks as graphs, Clustering of graphs, direct discovery
of communities in graphs, Partitioning of graphs, Neighbourhood properties in graphs.
UNIT - V Lecture Hrs:9
Data Visualization: Basic principles, ideas and tools for data visualization, Examples of inspiring
(industry) projects.
Data Science and Ethical Issues: Discussions on privacy, security, ethics, a look back at Data
Science, Next-generation data scientists.
Textbooks:
12
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

1. Cathy O‘Neil and Rachel Schutt. Doing Data Science, Straight Talk from the
Frontline. O‘Reilly. 2014.
Reference Books:
1. Jure Leskovek, AnandRajaraman and Jeffrey Ullman. Mining of Massive Datasets.
v2.1,Cambridge University Press. 2014. (free online)
2. Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. ISBN 0262018020. 2011
3. Foster Provost and Tom Fawcett. Data Science for Business: What You Need to Know
aboutData Mining and Data-analytic Thinking. ISBN 1449361323. 2013
Online Learning Resources:
SOURCE LINK:
https://jntuacea.ac.in/pdfs/B%20Tech%20CSE%20R17%20Syllabus.pdf

13
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code INFORMATION RETRIEVAL L T P C

21D25102b (Common to M.Tech. SE,AI & ML) 3 0 0 3
Semester I

Course Objectives:
• To provide an overview of Information Retrieval
• To introduce students about insights of the several topics of Information retrieval such as –
Boolean retrieval model, Vector space model, Latent semantic indexing, XML and Image
retrieval model
• To provide comprehensive details about various Evaluation methods
• To provide implementational insight about the topics covered in the course.
Course Outcomes (CO): Student will be able to
• Analyze and implement algorithms to extract relevant information from unstructured data
using Information retrieval techniques.
• Evaluate information retrieval algorithms for document indexing, relevance ranking, web
search, query processing, recommender systems, etc.
• Apply various information retrieval techniques to retrieve information.
• Create information retrieval applications based on various ranking principles and retrieval
methods.
UNIT – I Lecture Hrs:8
Boolean Retrieval
An example information retrieval problem, A first take at building an inverted index, Processing
Boolean queries, The extended Boolean model versus ranked retrieval.
The term Vocabulary and Postings Lists
Document delineation and character sequence decoding, Obtaining the character sequence in a
document, Choosing a document unit, Determining the vocabulary of terms, Tokenization, Dropping
common terms: stop words, Normalization (equivalence classing of terms), Stemming and
lemmatization, Faster postings list intersection via skip pointers, Positional postings and phrase
queries, Bi-word indexes, Positional indexes, Combination schemes.
UNIT - II Lecture Hrs:8
Dictionaries and tolerant retrieval
Search structures for dictionaries, Wildcard queries, General wildcard queries, k-gram indexes for
wildcard queries, Spelling correction, Implementing spelling correction, Forms of spelling
correction, Edit distance, k-gram indexes for spelling correction, Context sensitive spelling
correction, Phonetic correction
Index Construction:Hardware basics, Blocked sort-based indexing, Single-pass in-memory
indexing, Distributed indexing, Dynamic indexing and Other types of indexes.
UNIT - III Lecture Hrs:8
Index compression
Statistical properties of terms in information retrieval, Heaps’ law: Estimating the number of terms,
Zipf’s law: Modeling the distribution of terms, Dictionary compression, Dictionary as a string,
Blocked storage.
Scoring, term weighting and the vector space model
Parametric and zone indexes, Weighted zone scoring, Learning weights, The optimal weight g, Term
frequency and weighting, Inverse document frequency, TF-IDF weighting, The vector space model
for scoring, Dot products, Queries as vectors, Computing vector scores.
UNIT - IV Lecture Hrs:8

14
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Computing scores in a complete search system

Efficient scoring and ranking, Inexact top K document retrieval, Index elimination, Champion lists,
Static quality scores and ordering, Impact ordering, Cluster pruning, Components of an information
retrieval system, Tiered indexes, Query-term proximity, Designing parsing and scoring functions.
Putting it all together.
Evaluation in information retrieval
Information retrieval system evaluation, Standard test collections, Evaluation of unranked retrieval
sets, Evaluation of ranked retrieval results.
UNIT - V Lecture Hrs:7
XML retrieval: Basic XML concepts, Challenges in XML retrieval, A vector space model for XML
retrieval, Evaluation of XML retrieval, Text-centric vs. data-centric XML retrieval.
Probabilistic information retrieval
Review of basic probability theory, The Probability Ranking Principle, The Binary Independence
Model.
Textbooks:
1. An Introduction to Information Retrieval, Christopher D. Manning, PrabhakarRaghavan,
HinrichSchütze:, Cambridge University Press, England, 2008, ISBN 13: 9780521865715.
2. Statistical Language Models for Information Retrieval, ChengXiangZhai, , Morgan &
Claypool Publishers, 2009, ISBN: 9781598295900
Reference Books:
1. Modern Information Retrieval, Ricardo Baeza-Yates, BerthierRibeiro-Neto, Addison Wesley
Longman Publishing Co. Inc, 2009, ISBN-10: 0321416910.
2. Information Retrieval Data Structures and Algorithms,William B. Frakes, Ricardo Baeza-Yates,
First Edition, Pearson Education Limited,2012, ISBN-9788131716922.

15
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code ADVANCED DATA STRUCTURES AND L T P C

21D58101 ALGORITHMS 3 0 0 3
(Common to M.Tech CSE, CN, SE,AI & ML)
Semester I

Course Objectives:
 To understand concepts of dictionaries and hash tables.
 To implement lists and trees.
 To analyze usage of B trees, Splay trees and 2-3 trees.
 To understand the importance of text processing and computational Geometry.
Course Outcomes (CO): Student will be able to
 Understand the implementation of symbol table using hashing techniques
 Apply advanced abstract data type (ADT) and data structures in solving real world
 problem
 Effectively combine the fundamental data structures and algorithmic techniques in
 building a solution to a given problem
 Develop algorithms for text processing applications
UNIT - I Lecture Hrs:
Dictionaries : Definition, Dictionary Abstract Data Type, Implementation of Dictionaries, Hashing:
Review of Hashing, Hash Function, Collision Resolution Techniques in Hashing, Separate Chaining,
Open Addressing, Linear Probing, Quadratic Probing, Double Hashing, Rehashing, Extendible
Hashing.
UNIT - II Lecture Hrs:
Skip Lists : Need for Randomizing Data Structures and Algorithms, Search and Update Operations on
Skip Lists, Probabilistic Analysis of Skip Lists, Deterministic Skip Lists, Trees: Binary Search Trees
(BST), AVL Trees, Red Black Trees: Height of a Red Black Tree, Red Black Trees Bottom-Up
Insertion, Top-Down Red Black Trees, Top-Down Deletion in Red Black Trees, Analysis of
Operations.
UNIT - III Lecture Hrs:
2-3 Trees , Advantage of 2-3 trees over Binary Search Trees, Search and Update Operations on 2-3
Trees, Analysis of Operations, B-Trees: Advantage of B- trees over BSTs, Height of B-Tree, Search and
Update Operations on 2-3 Trees, Analysis of Operations, Splay Trees: Splaying, Search and Update
Operations on Splay Trees, Amortized Analysis of Splaying.
UNIT - IV Lecture Hrs:
Text Processing: Sting Operations, Brute-Force Pattern Matching, The Boyer-Moore Algorithm, The
Knuth-Morris-Pratt Algorithm, Standard Tries, Compressed Tries, Suffix Tries, TheHuffman Coding
Algorithm, The Longest Common Subsequence Problem (LCS), Applying Dynamic Programming to
the LCS Problem
UNIT - V Lecture Hrs:
Computational Geometry: One Dimensional Range Searching, Two Dimensional Range Searching,
Constructing a Priority Search Tree, Searching a Priority Search Tree, Priority Range Trees, Quadtrees,
k-D Trees.
Textbooks:
1. Mark Allen Weiss, Data Structures and Algorithm Analysis in C++, second Edition, Pearson, 2004.
2. T.H. Cormen, C.E. Leiserson, R.L.Rivest, Introduction to Algorithms, Third Edition Prentice Hall,
2009
Reference books:
1. Michael T. Goodrich, Roberto Tamassia, Algorithm Design, First Edition, Wiley, 2006.

16
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code R PROGRAMMING LAB L T P C

21D97103 0 0 4 2
Semester I

Course Objectives:
 To implement installation of R in windows.
 To implement data types.
 To implement descriptive statistics using R.
 To implement visualization techniques in R.
Course Outcomes (CO):
 Implement installation of R in windows.
 Implement data types.
 Implement descriptive statistics using R.
 Implement visualization techniques in R.
List of Experiments:
1. Installation of R Installing R in windows, R Console (R window to edit and execute R
Commands), Commands and Syntax (R commands and R syntax), Packages and Libraries
(Install and load a package in R), Help In R, Workspace in R.
2. Implement the data structures using R Programming Introduction to Data Types (Why Data
Structures?, Types of Data Structures in R), Vectors, Matrices, Arrays, Lists, Factors, Data
Frames, Importing and Exporting Data.
3. Implement the Graphical Analysis using R Creating a simple graph (Using plot() command),
Modifying the points and lines of a graph (Using type, pch, font, cex, lty, lwd, col arguments
in plot() command), Modifying Title and Subtitle of graph (Using main, sub, col.main,
col.sub, cex.main, cex.sub, font.main, font.sub arguments in plot() command), Modifying
Axes of a Graph (Using xlab, ylab, col.lab, cex.lab, font.lab, xlim, ylim, col.axis, cex.axis,
font.axis arguments and axis() command), Adding Additional Elements to a Graph (Using
points(), text(), abline(), curve() commands), Adding Legend on a Graph (Using legend()
command), Special Graphs (Using pie(), barplot(), hist() commands), Multiple Plots (Using
mfrow or mfcol arguments in par() command and layout command).
4. Implement the Descriptive Statistics using R. Measure of Central Tendency (Mean, Median
and Mode), Measure of Positions (Quartiles, Deciles, Percentiles and Quantiles), Measure of
Dispersion (Range, Median, Absolute deviation about median, Variance and Standard
deviation), Measure of Distribution (Skewness and Kurtosis), Box and Whisker Plot (Box
Plot and its parts, Using Box Plots to compare distribution).
5. Extract data from files and other sources and perform various data manipulation tasks on
them.
6. Use R Graphics and Tables to visualize results of various statistical operations on data.
7. Apply the knowledge of R gained to aplly for data analytics in real life applications.
8. Extend the functionality of R using add on packages.

17
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
Course Code ARTIFICAL INTELLEGENCE LAB L T P C
21D97104 0 0 4 2
Semester I
Course Objectives:
• Students will have the successful careers in the field of computer science and allied
sectors as an innovative engineer.
• Students will continue to learn and advance their careers through participation in
professional activities, attainment of professional certification and seeking advance
studies.
• Students will be able to demonstrate a commitment to life-long learning.
• Students will be ready to serve society in any manner and become a responsible
and aware citizen.
• Establishing students in a leadership role in any field

Course Outcomes (CO):

• Write a python program to implement simple Chatbot
• To apply various search algorithms of artificial intelligence.
• To apply knowledge representation and reasoning techniques.
• To understand & apply different types of machine learning and models
• To understand the design principles of pattern recognition with estimation and
apply classification technique.
List of Experiments:
1.Write a program in prolog to implement simple facts and Queries
2. Write a program in prolog to implement simple arithmetic
3. Write a program in prolog to solve Monkey banana problem
4. Write a program in prolog to solve Tower of Hanoi
5. Write a program in prolog to solve 8 Puzzle problems
6. Write a program in prolog to solve 4-Queens problem
7. Write a program in prolog to solve Traveling salesman problem
8. Write a program in prolog for Water jug problem
9. Write a program to implement a Tic-Tac-Toe game.
10. Write a python program to implement simple Chatbot?
References:

18
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code RESEARCH METHODOLOGY AND IPR L T P C

21DRM101 (Common to M.Tech CSE, CN, SE,AI & ML) 2 0 0 2
Semester I

Course Objectives:
• Identify an appropriate research problem in their interesting domain.
• Understand ethical issues understand the Preparation of a research project thesis report.
• Understand the Preparation of a research project thesis report
• Understand the law of patent and copyrights.
• Understand the Adequate knowledge on IPR
Course Outcomes (CO): Student will be able to
 Analyze research related information
 Follow research ethics
 Understand that today’s world is controlled by Computer, Information Technology, but tomorrow
world will be ruled by ideas, concept, and creativity.
 Understanding that when IPR would take such important place in growth of individuals & nation, it is
needless to emphasis the need of information about Intellectual Property Right to be promoted among
students in general & engineering in particular.
 Understand that IPR protection provides an incentive to inventors for further research work and
investment in R & D, which leads to creation of new and better products, and in turn brings about,
economic growth and social benefits.
UNIT - I Lecture Hrs:
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 - II Lecture Hrs:
Effective literature studies approaches, analysis Plagiarism, Research ethics, 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 - III Lecture Hrs:
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 - IV Lecture Hrs:
Patent Rights: Scope of Patent Rights. Licensing and transfer of technology. Patent information and databases.
Geographical Indications.
UNIT - V
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.
Textbooks:
1. Stuart Melville and Wayne Goddard, “Research methodology: an introduction for science &
engineering students’”
2. Wayne Goddard and Stuart Melville, “Research Methodology: An Introduction”
Reference Books:
1. Ranjit Kumar, 2nd Edition, “Research Methodology: A Step by Step Guide for
beginners”
2. Halbert, “Resisting Intellectual Property”, Taylor & Francis Ltd ,2007.
3. Mayall, “Industrial Design”, McGraw Hill, 1992.
4. Niebel, “Product Design”, McGraw Hill, 1974.
5. Asimov, “Introduction to Design”, Prentice Hall, 1962.
6. Robert P. Merges, Peter S. Menell, Mark A. Lemley, “ Intellectual Property in New
Technological Age”, 2016.
19
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code ADVANCED DATA MINING L T P C

21D97201 3 0 0 3
Semester II
Course Objectives:
• To analyze Algorithms for sequential patterns.
• To extract patterns from time series data.
• To develop algorithms for Temporal Patterns.
• To identify computing frameworks for Big Data
analytics.
• To extend the Graph mining algorithms to Web
Mining
Course Outcomes (CO): Student will be able to
• Analyze Algorithms for sequential patterns.
• Extract patterns from time series data.
• Develop algorithms for Temporal Patterns.
• Identify computing frameworks for Big Data
analytics.
• Extend the Graph mining algorithms to Web Mining
UNIT - I Lecture Hrs:8
Review of Frequent Item set Mining. Sequential Pattern Mining concepts, primitives, scalable
methods; Closed Sequential Patterns.
UNIT - II Lecture Hrs:8
Transactional Patterns and other temporal based frequent patterns, Mining Time series Data,
Periodicity Analysis for time related sequence data, Trend analysis, Similarity search in Time-series
analysis.
UNIT - III Lecture Hrs:9
Graph Mining, Mining frequent sub-graphs, finding clusters, hub and outliers in large graphs, Graph
Partitioning; Web Mining.
UNIT – IV Lecture Hrs:9
Classification- Decision Tree learning, Bayesian Learning, Class Imbalance Problem. Review of
Clustering methods.
UNIT – V Lecture Hrs:9
Trajectory Pattern Mining: Moving together patterns, Sequential Pattern mining from trajectories,
Trajectory Clustering.
Textbooks:
1. Jiawei Han and M Kamber, Data Mining Concepts and Techniques, Second Edition, Elsevier
Publication,2011.
2. Vipin Kumar, Pang-Ning Tan, Michael Steinbach, Introduction to Data Mining, Addison
Wesley,2006.
Reference Books:
1. Introduction to Data Mining , Tan steinbach, Kumar.
2. Data Mining Techniques: Gordon S Linoff&Micael J Berry, Wiley Publications, Third Edition.
Online Learning Resources:
Coursera.org

20
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code DEEP LEARNING L T P C

21D58203a 3 0 0 3
Semester II

Course Objectives:
• To identify Convolutional Neural Networks models to solve Supervised Learning
Problems
• To design Autoencoders to solve Unsupervised Learning problems
• To apply Long Shot Term Memory (LSTM) Networks for time series analysis
classification problems.
• To apply Classical Supervised Tasks for Image Denoising, Segmentation and Object
detection problems.
Course Outcomes (CO): Student will be able to
• Identify Convolutional Neural Networks models to solve Supervised Learning Problems
• Design Autoencoders to solve Unsupervised Learning problems
• Apply Long Shot Term Memory (LSTM) Networks for time series analysis classification
problems.
• Apply Classical Supervised Tasks for Image Denoising, Segmentation and Object
detection problems.
UNIT - I Lecture Hrs:9
Introduction to Biological Neurons, Artificial Neural Networks, McCulloch Pitts Neuron, Learning
processes, Perceptron, Perceptron convergence theorem, XOR problem, Multilayer perceptron, Back
Propagation (BP) Learning.
UNIT - II Lecture Hrs:9
Activation functions: Sigmoid, Linear, Tanh, ReLU, Leaky ReLU, SoftMax, loss functions, First and
Second order optimization methods, Optimizers: Gradient Descent (GD), Batch Optimization,
Momentum Based GD, Stochastic GD, AdaGrad, RMSProp, Adam; Introduction to Self Organizing
Maps; Sequence to sequence models, RNN, Vanishing and Exploding Gradients, GRU, LSTM for
NLP Applications.
UNIT - III Lecture Hrs:9
Convolutional Neural Network, Building blocks of CNN, Transfer Learning; Regularization: Bias
Variance Tradeoff, L2 regularization, Early stopping, Dataset augmentation, Parameter sharing and
tying, Dropout.
UNIT - IV Lecture Hrs:9
Autoencoders : Unsupervised Learning with Deep Network, Autoencoders, Stacked, Sparse,
Denoising Autoencoders, Variational Autoencoders; Recent Trends in Deep Learning Architectures,
Residual Network, Skip Connection Network, GoogleNet, DensenNet, SqueezNet, MobileNet,
NasNet Models.
UNIT - V Lecture Hrs:9
Classical Supervised Tasks with Deep Learning, Segmentation Unet, FCN models, Object
Localization (RCNN), FRCNN with Applications; Transformer, Generative Adversarial Network,
Design own neural network models on Image, vision and NLP Applications..
Textbooks:
1. Deep Learning- Ian Good felllow, YoshuaBenjio, Aaron Courville, The MIT Press.
2. Christopher Bishop, Pattern Recognition and Machine Learning, Springer,2006.
Reference Books:
1. Simon Haykin, “Neural Networks, A Comprehensive Foundation”, 2nd Edition, Addison
Wesley Longman, 2001.

21
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
2. Deep Learning From Scratch: Building with Python from First Principles by Seth Weidman
published by O`Reilley
3. Grokking Deep Learning by Andrew W. Trask published by Manning Publications

22
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code DATA ANALYTICS L T P C

21D58301c (Common to M.Tech CSE, SE,AI&ML) 3 0 0 3
Semester II

Course Objectives:
• To explore the fundamental concepts of data analytics.
• To learn the principles and methods of statistical analysis
• Discover interesting patterns, analyze supervised and unsupervised models and estimate the
accuracy of the algorithms.
• To understand the various search methods and visualization techniques.
Course Outcomes (CO): Student will be able to
 Understand the ideas of statistical approaches to learning
 Understand the significance of exploratory data analysis (EDA) in data science and apply basic tools
(plots, graphs, summary statistics) to perform EDA
 Apply basic machine learning algorithms (Linear Regression, k-Nearest Neighbors (k-NN), k-means,
Naive Bayes) for predictive modeling. Explore the merits of Naive Bayes technique
 Recognize the characteristics of machine learning techniques that are useful to solve real-world
problems
UNIT - I Lecture Hrs:
Introduction: What is Data Science? Big Data and Data Science hype and getting past the hype, Why now?,
Datafication, Current landscape of perspectives, Skill sets, Life cycle of Data Science, Different phases.
UNIT - II Lecture Hrs:
Exploratory Data Analysis and the Data Science Process: Basic tools (plots, graphs and summary statistics) of
EDA, Philosophy of EDA, The Data Science Process, Case Study: RealDirect (online real estate firm), Three
Basic Machine Learning Algorithms: Linear Regression, k-Nearest Neighbours (k-NN), k-means.
UNIT - III Lecture Hrs:
One More Machine Learning Algorithm and Usage in Applications: Motivating application: Filtering Spam,
Why Linear Regression and k-NN are poor choices for Filtering Spam, Naive Bayes and why it works for
Filtering Spam, Data Wrangling: APIs and other tools for scrapping the Web, Feature Generation and Feature
Selection (Extracting Meaning From Data), Motivating application: user (customer) retention,
UNIT - IV Lecture Hrs:
Feature Generation (brainstorming, role of domain expertise, and place for imagination), Feature Selection
algorithms: Filters; Wrappers; Decision Trees; Random Forests, Recommendation Systems: Building a User-
Facing Data Product: Algorithmic ingredients of a Recommendation Engine, Dimensionality Reduction,
Singular Value Decomposition, Principal Component Analysis, Exercise: build your own recommendation
system.
UNIT - V Lecture Hrs:
Data Visualization: Basic principles, ideas and tools for data visualization, Case study on industry projects,
Exercise: create your own visualization of a complex dataset, Data Science and Ethical Issues: Discussions on
privacy, security, ethics, A look back at Data Science, Next-generation data scientists.
Textbooks:
1. Cathy O'Neil and Rachel Schutt. Doing Data Science, Straight Talk From The Frontline. O'Reilly,
2014.
2. Jure Leskovek, AnandRajaraman and Jerey Ullman. Mining of Massive Datasets, Cambridge
University Press, 2014.
Reference Books:
1. Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. MIT Press, 2013.
2. Foster Provost and Tom Fawcett. Data Science for Business: What You Need to Know about Data
Mining and Data-analytic Thinking. O′Reilly, 2013.
3. Trevor Hastie, Robert Tibshirani and Jerome Friedman. Elements of Statistical Learning, Second
Edition. Springer, 2009.
4. Avrim Blum, John Hopcroft and RavindranKannan. Foundations of Data Science.2018.
23
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
5. Mohammed J. Zaki and Wagner Miera Jr. Data Mining and Analysis: Fundamental Concepts and
Algorithms. Cambridge University Press, 2014.
6. Jiawei Han, MichelineKamber and Jian Pei. Data Mining: Concepts and Techniques, Third
Edition. Morgan Kaufmann, 2011.

24
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code PATTERN RECOGNITION L T P C

21D97203a 3 0 0 3
Semester II

Course Objectives:
 The objective of the course is to understand the algorithms for Pattern Recognition. The
representation of patterns and classes and the similarity measures are an important aspect of
pattern recognition. Pattern recognition involves classification and clustering of patterns.
The two well-known paradigms of machine learning namely, learning from examples or
supervised learning and learning from observations or clustering covered in this course.
Course Outcomes (CO): Student will be able to
 Differentiate between supervised and unsupervised classifiers
 Classify the data and identify the patterns.
 Extract feature set and select the features from given data set.
 Apply fuzzy logic and genetic algorithms for classification problems, design systems and
algorithms for pattern recognition, with focus on sequences of patterns that are analyzed
using, e.g., hidden Markov models (HMM).
 Analyze classification problems probabilistically and estimate classifier performance.
 Understand and analyze methods for automatic training of classification systems.
 Apply Maximum-likelihood parameter estimation in relatively complex probabilistic models,
such as mixture density models and hidden Markov models.
UNIT - I Lecture Hrs:9
Overview of Pattern recognition – Basics of Probability and Statistics, Linear Algebra, Linear
Transformations, Components of Pattern Recognition System, Learning and adaptation Discriminant
functions – Supervised learning – Parametric estimation – Maximum Likelihood Estimation –
Bayesian parameter Estimation – Problems with Bayes approach– Pattern classification by distance
functions – Minimum distance pattern classifier.
UNIT - II Lecture Hrs:8
Clustering for unsupervised learning and classification–Clustering concept – C Means algorithm –
Hierarchical clustering – Graph theoretic approach to pattern Clustering – Validity of Clusters.
UNIT - III Lecture Hrs:9
Feature Extraction and Feature Selection: Feature extraction – discrete cosine and sine transform,
Discrete Fourier transform, Principal Component analysis, Kernel Principal Component Analysis.
Feature selection – class separability measures, Feature Selection Algorithms - Branch and bound
algorithm, sequential forward / backward selection algorithms. Principle component analysis,
Independent component analysis, Linear discriminant analysis, Feature selection through functional
approximation – Elements of formal grammars, Syntactic description – Stochastic grammars –
Structural Representation.
UNIT - IV Lecture Hrs:8
State Machines – Hidden Markov Models – Training – Classification – Support vector Machine –
Feature Selection.
UNIT - V Lecture Hrs:8
Fuzzy logic – Fuzzy Pattern Classifiers – Pattern Classification using Genetic Algorithms – Case
Study Using Fuzzy Pattern Classifiers and Perception.
Textbooks:
1. Andrew Webb, “Stastical Pattern Recognition”, Arnold publishers, London,1999
Reference Books:
1. C.M.Bishop, “Pattern Recognition and Machine Learning”, Springer, 2006.
25
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
2. M. Narasimha Murthy and V. Susheela Devi, “Pattern Recognition”, Springer 2011.
3. Menahem Friedman, Abraham Kandel, “Introduction to Pattern Recognition Statistical,
Structural, Neural and Fuzzy Logic Approaches”, World Scientific publishing Co. Ltd, 2000.
4. . Robert J.Schalkoff, “Pattern Recognition Statistical, Structural and Neural Approaches”,
John Wiley & Sons Inc., New York, 1992.
5. . R.O.Duda, P.E.Hart and D.G.Stork, “Pattern Classification”, John Wiley, 2001
6. . S.Theodoridis and K.Koutroumbas, “Pattern Recognition”, 4th Ed., Academic Press. 2009.

26
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code INTELLIGENT AGENT SYSTEMS L T P C

21D97203b 3 0 0 3
Semester II

Course Objectives:
• To understand the fundamentals of key intelligent systems technologies
• To understand hybrid intelligent systems
• To understand evolutionary computation
• To practice in an integration of intelligent systems technologies for engineering applications.
Course Outcomes (CO): Student will be able to
• Explain the fundamentals of key intelligent systems technologies
• Describe neural networks, fuzzy systems, and evolutionary computation.
• Explain the hybrid intelligent systems
• List the integration of intelligent systems technologies for engineering applications.
UNIT - I Lecture Hrs:9
Introduction: Computational Intelligence: Intelligence machines -Computational intelligence
paradigms –History- Expert Systems: Rule-based expert systems – Uncertainty management - Fuzzy
expert systems: Fuzzy sets and operations of fuzzy sets - Fuzzy rules and fuzzy inference - Fuzzy
expert systems
UNIT - II Lecture Hrs:9
Artificial Neural Networks: Fundamental neurocomputing concepts: artificial neurons, activation
functions, neural network architectures, learning rules - Supervised learning neural networks: multi-
layer feed forward neural networks, simple recurrent neural networks, time-delay neural networks,
supervised learning algorithms - Unsupervised learning neural networks: self-organizing feature
maps - Radial basis function networks - Deep neural networks and learning algorithms
UNIT – III Lecture Hrs:8
Evolutionary computation: Representation: Chromosomes-fitness functions- selection mechanisms
-Genetic algorithms: crossover and mutation - Genetic programming
UNIT – IV Lecture Hrs:8
Hybrid Intelligent Systems: Neural expert systems -Neuro-fuzzy systems -Evolutionary neural
networks
UNIT – V Lecture Hrs:9
Applications and case studies: Printed Character Recognition – Inverse Kinematics Problems –
Automobile Fuel Efficiency Prediction – Soft Computing for Color Recipe Prediction-Case studies.
Textbooks:
1. A.P. Engelbrecht, Computational Intelligence: An Introduction, 2012,2nd Edition, John
Wiley & Sons.
2. S.Rajasekaran and G.A. Vijayalakshmi Pai, Neural Networks, Fuzzy logic and Genetic
Algorithms-Synthesis and Applications, 2003, PHI Learning
Reference Books:
1. Marsland S, Machine Learning: An Algorithmic Perspective, 2009, CRC Press.
2. S. Russell and P. Norvig, Artificial Intelligence – A Modern Approach,2010, Prentice Hall.
3. J.S.R.Jang, C.T.Sun and E.Mizutani, Neuro-Fuzzy and Soft Computing, 2004, PHI, Pearson
Education.

27
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code INTRUSION DETECTION SYSTEMS L T P C

21D97204c 3 0 0 3
Semester II

Course Objectives:
• To understand when, where, how, and why to apply Intrusion Detection tools and techniques
in order to improve the security posture of an enterprise.
• Apply knowledge of the fundamentals and history of Intrusion Detection in order to avoid
common pitfalls in the creation and evaluation of new Intrusion Detection Systems.
• Analyze intrusion detection alerts and logs to distinguish attack types from false alarms.
• To be able to analyze the basic Firewall mechanism.
Course Outcomes (CO): Student will be able to
• Acquire knowledge of Intrusion Detection.
• Ability to improve the security posture of any enterprise by applying the intrusion
mechanism.
• Ability to design new Intrusion Detection Systems in the lower level.
• Identify attack types from false alarms.
UNIT - I Lecture Hrs:9
History of Intrusion Detection: Audit, Concept and definition, Internal and external threats to data,
attacks, Need and types of IDS, Information sources Host based information sources, Network based
information sources.
UNIT - II Lecture Hrs:10
Intrusion Prevention System and Snort: Network IDs protocol based IDs, Hybrid IDs, Analysis
schemes, thinking about intrusion. A model for intrusion analysis- Incident Responses – Incident
Response Process – IDS ad IPS response Phases Forensics –Corporate Issues - Snort Installation
Scenarios, Installing Snort, Running Snort on Multiple Network Interfaces, Snort Command Line
Options. Step-By-Step Procedure to Compile and Install Snort Location of Snort Files, Snort Modes
Snort Alert Modes
UNIT - III Lecture Hrs:10
Snort Rules and ACID: Rule Headers, Rule Options, the Snort Configuration File etc. Plugins,
Preprocessors and Output Modules, Using Snort with MySQL - Using ACID and Snort Snarf with
Snort -Agent development for intrusion detection - Architecture models of IDs and IPs.
UNIT - IV Lecture Hrs:10
Firewall Introduction and Technologies: Why Internet Firewalls - Internet Services - Security
Strategies - Building Firewalls - Packets and Protocols - What Does a Packet Look Like? - IP -
Protocols Above IP - Protocols Below IP - Application Layer Protocols - IP Version - Non-IP
Protocols - Attacks Based on Low-Level Protocol Details - Firewall Technologies - Some Firewall
Definitions - Packet Filtering - Proxy Services - Network Address Translation - Virtual Private
Networks
UNIT - V Lecture Hrs:9
Building Firewalls:Firewall Architectures - Firewall Design - Packet Filtering - Proxy Systems -
Bastion Hosts - UNIX and Linux Bastion Hosts 176 - Windows NT and Windows 2000 Bastion
Hosts
Textbooks:
1. RafeeqRehman , “ Intrusion Detection with SNORT, Apache, MySQL, PHP and ACID,” 1st
Edition, Prentice Hall , 2003.
2. Carl Endorf, Eugene Schultz and Jim Mellander“Intrusion Detection & Prevention”, 1st Edition,
Tata McGraw-Hill, 2004.
3. Elizabeth D. Zwicky, Simon Cooper & D. Brent Chapman , “Building Internet Firewalls“ O’Reilly

28
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Reference Books:
1. Christopher Kruegel,FredrikValeur, Giovanni Vigna: “Intrusion Detection and Correlation
Challenges and Solutions”, 1st Edition, Springer, 2005.
2. Stephen Northcutt, Judy Novak : “Network Intrusion Detection”, 3rd Edition, New Riders
Publishing, 2002.
3. T. Fahringer, R. Prodan, “A Text book on Grid Application Development and Computing
Environment”. 6th Edition,KhannaPublihsers, 2012.

29
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code COMPUTER VISION L T P C

21D58203c (Common to M.Tech CSE, AI & ML) 3 0 0 3
Semester II

Course Objectives:
 Be familiar with both the theoretical and practical aspects of computing with images.
 Have described the foundation of image formation, measurement, and analysis.
 Understand the geometric relationships between 2D images and the 3D world.
 Grasp the principles of state-of-the-art deep neural networks
Course Outcomes (CO): Student will be able to
 Develop the practical skills necessary to build computer vision applications.
 To have gained exposure to object and scene recognition and categorization from images
UNIT - I Lecture Hrs:
Overview, computer imaging systems, lenses, Image formation and sensing,
Image analysis, pre-processing and Binary image analysis
UNIT - II Lecture Hrs:
Edge detection, Edge detection performance, Hough transform, corner detection
UNIT - III Lecture Hrs:
Segmentation, Morphological filtering, Fourier transform
UNIT - IV Lecture Hrs:
Feature extraction, shape, histogram, colour, spectral, texture, using CVIPtools, Feature analysis, feature
vectors, distance /similarity measures, data pre-processing
UNIT - V Lecture Hrs:
Pattern Analysis:
Clustering: K-Means, K-Medoids, Mixture of Gaussians, Classification: Discriminant Function, Supervised,
Un-supervised, Semi supervised
Classifiers: Bayes, KNN, ANN models; Dimensionality Reduction: PCA, LDA, ICA, and Non-parametric
methods
Textbooks:
1. Computer Vision: Algorithms and Applications by Richard Szeliski.
Reference Books:
1. Deep Learning, by Goodfellow, Bengio, and Courville.
2. Dictionary of Computer Vision and Image Processing, by Fisher et al.

30
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code NATURAL LANGUAGE PROCESSING L T P C

21D97204b 3 0 0 3
Semester II

Course Objectives:
• To be able to tag a given word with basic language processing features
• To be able to discuss the current and likely future performance of several NLP applications;
• To be able to describe briefly a fundamental technique for processing language for several
subtasks, such as morphological processing, parsing, word sense disambiguation etc.
• To understand how these techniques draw on and relate to other areas of Computer Science.
Course Outcomes (CO): Student will be able to
• Describe the current and likely future performance of several NLP applications.
• Explain how these techniques draw on and relate to other areas of Computer Science.
• Describe the processing language for subtasks
• List the language processing features
UNIT - I Lecture Hrs:9
Introduction to NLP : Knowledge in Speech and Language Processing -–Information Theory-
Ambiguity Models and Algorithms, Language : N-gram Language Models - Evaluating Language
Models, Thought and Understanding - The State of the Art and the Near term Future
UNIT - II Lecture Hrs:9
Speech Tagging and Transducers: Part of Speech Tagging, Probability Basics: Hidden Markov -
Maximum Entropy Models, Word Transducers: Finite State Transducers - Orthographic Rules -
Finite-State Transducers Combining FST Lexicon Rules, Lexicon Free FSTs: The Porter Stemmer
Human Morphological Processing.
UNIT - III Lecture Hrs:9
Syntax Parsing: Syntax Parsing: Grammar Formalisms - Tree Banks - Parsing with Context Free
Grammars - Features and Unification, Statistical parsing: probabilistic CFGs (PCFGs) - Lexicalized
PCFG
UNIT - IV Lecture Hrs:9
Semantic Analysis: Representing Meaning – Semantic Analysis - Lexical Semantics –
Computational Lexical Semantics - Supervised – Dictionary based and Unsupervised Approaches -
Compositional Semantics - Semantic Role Labelling - Semantic Parsing – Discourse Analysis.
UNIT - V Lecture Hrs:9
Case Studies and Applications: Machine Translation Language Similarities and Differences -
Named Entity Recognition and Relation Extraction- IE using sequence labelling-Machine
Translation (MT) - Basic issues in MT-Statistical translation - Word Alignment - Phrase-based
Translation – Question Answering
Textbooks:
1. Daniel Jurafsky and James H. Martin, Martin Speech and Language Processing, 2008, 2nd Edition,
Prentice Hall.
2. Christopher D. Manning and HinrichSchuetze, Foundations of Statistical Natural Language
Processing, 1999, MIT Press.
Reference Books:
1. James Allen, Natural Language Understanding, 1994, 2nd Edition, Addison Wesley.
2. Steven Bird, Ewan Klein and Edward Loper, Natural Language Processing with Python, O’Reilly
Media, 2009, 1st Edition.

31
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code ADVANCED DATA MINING LAB L T P C

21D97205 0 0 4 2
Semester II

Course Objectives:
• To implement knowledge discovery.
• To design several OLTP and OLAP processes for various real time applications.
• To evaluate various case study on risk assessment.
Course Outcomes (CO):
• Implement knowledge discovery.
• Design several OLTP and OLAP processes for various real time applications.
• Evaluate various case study on risk assessment.
List of Experiments:
Credit Risk Assessment:
The business of banks is making loans. Assessing the credit worthiness of an applicant is of crucial
importance. You have to develop a system to help a loan officer decide whether the credit of a
customer is good, or bad. A bank's business rules regarding loans must consider two opposing
factors. On the one hand, a bank wants to make as many loans as possible. Interest on these loans is
the banks profit source. On the other hand, a bank cannot afford to make too many bad loans. Too
many bad loans could lead to the collapse of the bank. The bank's loan policy must involve a
compromise: not too strict, and not too lenient. To do the assignment, you first and foremost need
some knowledge about the world of credit.
You can acquire such knowledge in a number of ways.
1. Knowledge Engineering. Find a loan officer who is willing to talk. Interview her and
try to represent her knowledge in the form of production rules.
2. Books. Find some training manuals for loan officers or perhaps a suitable textbook on
finance. Translate this knowledge from text form to production rule form.
3. Common sense. Imagine yourself as a loan officer and make up reasonable rules
which can be used to judge the credit worthiness of a loan applicant.
4. Case histories. Find records of actual cases where competent loan officers correctly
judged when, and when not to, approve a loan application.

The German Credit Data:

Actual historical credit data is not always easy to come by because of confidentiality rules. Here is
one such dataset, consisting of 1000 actual cases collected in Germany. Credit dataset (original)
Excel spreadsheet version of the German credit data.
In spite of the fact that the data is German, you should probably make use of it for this
assignment. (Unless you really can consult a real loan officer!)
A few notes on the German dataset
1. DM stands for Deutsche Mark, the unit of currency, worth about 90 cents Canadian
(but looks and acts like a quarter).
2. owns telephone. German phone rates are much higher than in Canada so fewer
people own telephones.
3. foreign worker. There are millions of these in Germany (many from Turkey). It is
very hard to get German citizenship if you were not born of German parents.
4. There are 20 attributes used in judging a loan applicant. The goal is to classify the
applicant into one of two categories, good or bad.

32
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code DEEP LEARNING LAB L T P C

21D97206 0 0 4 2
Semester II

Course Objectives:
• To implement Multilayer Feed Backward Neural network on MNIT digits dataset
• To construct RNN, LSTM, BiLSTM Networks for time series analysis classification
problems.
• To design Autoencoders to solve Unsupervised Learning problems
• To evaluate Classical Supervised Tasks for Image Denoising, Segmentation and Object
detection problems.
Course Outcomes (CO):
• Implement Multilayer Feed Backward Neural network on MNIT digits dataset
• Build RNN, LSTM, BiLSTM Networks for time series analysis classification problems.
• Design Autoencoders to solve Unsupervised Learning problems
• Implement Classical Supervised Tasks for Image Denoising, Segmentation and Object
detection problems.
List of Experiments:
Implement perceptron learning algorithm and attempt to solve two input i) AND gate ii) Or Gate iii)
EXOR gate problems.
1. Design and implement a perceptron learning algorithm and attempt to solve XOR problem
2. Implement a Multilayer Feed Backward Neural network algorithm on MNIT digits dataset.
3. Build your own Recurrent networks and Long short-term memory networks on IMDB movie
reviews classification data.
4. Design and implement a BiLSTM and BERT on given a product review dataset to classify the
review rating from 1 to 5 classes
5. Design and implement Autoencoders for credit card fraud detection.
6. Design and implement a Convolutional Neural Network for image classification on the Fashion-
MNIST dataset.
7. Implement a VGG19 model for image classification with and without Transfer Learning on
Grocery dataset.
8. Implement a U-Net convolutional neural network model on segmentation of electron microscopic
(EM) images of the brain dataset.
9. Implement a FRCNN algorithm for object detection on small object dataset.
References:

1. Deep Learning- Ian Goodfelllow, YoshuaBenjio, Aaron Courville, The MIT Press.
2. Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
3. Simon Haykin, “Neural Networks, A Comprehensive Foundation”, 2nd Edition, Addison Wesley
Longman, 2001 .

Online learning resources/Virtual labs:

33
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code REINFORCEMENT LEARNING L T P C

21D97301a (Common for MTech CSE, AI & ML) 3 0 0 3
Semester III

Course Objectives:
 Reinforcement Learning is a subfield of Machine Learning, but is also a general-purpose formalism
for automated decision-making and AI. This course introduces you to statistical learning techniques
where an agent explicitly takes actions and interacts with the world.
Course Outcomes (CO): Student will be able to
• Formulate Reinforcement Learning problems
• Apply various Tabular Solution Methods to Markov Reward Process Problems
• Apply various Iterative Solution methods to Markov Decision Process Problems
• Comprehend Function approximation methods
UNIT - I Lecture Hrs:
Introduction: Introduction to Reinforcement Learning (RL) – Difference between RL and Supervised
Learning, RL and Unsupervised Learning. Elements of RL, Markov property, Markov chains, Markov
reward process (MRP).
UNIT - II Lecture Hrs:
Evaluative Feedback - Multi-Arm Bandit Problem: An n-Armed Bandit Problem, Exploration vs
Exploitation principles, Action value methods, Incremental Implementation, tracking a non-stationary
problem, optimistic initial values, upper-confidence-bound action selection, Gradient Bandits. Introduction
to and proof of Bellman equations for MRPs
UNIT - III Lecture Hrs:
Introduction to Markov decision process (MDP), state and action value functions, Bellman expectation
equations, optimality of value functions and policies, Bellman optimality equations. Dynamic Programming
(DP): Overview of dynamic programming for MDP, principle of optimality, Policy Evaluation, Policy
Improvement, policy iteration, value iteration, asynchronous DP , Generalized Policy Iteration.
UNIT - IV Lecture Hrs:
Monte Carlo Methods for Prediction and Control: Overview of Monte Carlo methods for model free RL,
Monte Carlo Prediction, Monte Carlo estimation of action values, Monto Carlo Control, On policy and off
policy learning, Importance sampling. Temporal Difference Methods: TD Prediction, Optimality of TD(0),
TD Control methods - SARSA, Q-Learning and their variants.
UNIT - V Lecture Hrs:
Eligibility traces: n-Step TD Prediction, Forward and Backward view of TD(λ), Equivalence of forward and
backward view, Sarsa(λ),, Watkins’s Q(λ), Off policy eligibility traces using importance of sampling.
Function Approximation Methods: Value prediction with function approximation, gradient descent
methods, Linear methods, control with function approximation.
Textbooks:
1. Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction", 2nd Edition, The
MIT Press.
2. CsabaSzepesvari – Algorithms for Reinforcement Learning – Morgan & Claypool, 2010.
Reference Books:
1. Reinforcement Learning By Richard S. (University Of Alberta) Sutton,Andrew G. (Co-Director
Autonomous Learning Laboratory) Barto

34
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code GAME THEORY L T P C

21D97301b 3 0 0 3
Semester III

Course Objectives:
 To design games based on complete and incomplete information about the players.
 To evaluate games where players cooperate.
 To compute Nash equilibrium.
 To apply game theory in modeling network traffic and analyze auction strategy.
Course Outcomes (CO): Student will be able to
• Analyze games based on complete and incomplete information about the players
• Analyze games where players cooperate
• Compute Nash equilibrium
• Apply game theory to model network traffic
• Analyze auctions using game theory
UNIT - I Lecture Hrs:10
Games, Old and New; Games, Strategies, Costs, and Payoffs; Basic Solution Concepts Finding
Equilibria and Learning in Games; Refinement of Nash: Games with turns and Subgame Perfect
Equilibrium; Nash Equilibrium without Full Information: Bayesian Games; Cooperative Games,
Markets and Their Algorithmic Issues;
UNIT - II Lecture Hrs:10
Is the NASH-Equilibrium Problem NP-Complete?; The Lemke-Howson Algorithm; The Class
PPAD. Succinct Representations of Games; The Reduction; Correlated Equilibria; Bitmatrix Games
and Best Response Condition; Equilibria Via Labeled Polytopes; The Lemke-Howson Algorithm;
Integer Pivoting and Degenerate Games; Extensive Games and Their Strategic Form; Sub game
Perfect Equilibria; Computing Equilibria with SequenceForm.
UNIT - III Lecture Hrs:10
Model and Preliminaries; External Regret Minimization; Regret minimization and Game Theory;
Generic Reduction from External to Swap Regret; On the Convergence of Regret- Minimizing
Strategies to Nash Equilibrium in Routing Games; Fisher’s Linear Case and the Eisenberg –Gale
Convex Program; Checking if Given Prices are Equilibrium Prices; Two Crucial Ingredients of the
Algorithm; The Primal-Dual Schema in the Enhanced Setting;
UNIT - IV Lecture Hrs:9
Tight Sets and the Invariants; Balanced Flows; The Main Algorithm and Running Time; The Linear-
Case of Arrow-Debreu Model; Algorithm for Single-Source Multiple-Sink Markets; Fisher Model
with Homogeneous Consumers
UNIT - V Lecture Hrs:9
.Exchange Economics Satisfying WGS; Specific Utility Functions; Computing Nash Equilibria in
Tree Graphical Games; Graphical Games and Correlated Equilibria; Graphical Exchange Economies.
Textbooks:
1. Noam Nisan, Tim Roughgarden, Eva Tardos, Vijay V. Vazirani, Algorithmic Game Theory,
Cambridge University Press, 2007.
2. Ronald Cohn Jesse Russell, Algorithmic Game Theory, VSD Publishers, 2012.
Reference Books:
1. Theory of games and economic behavior by John Von Neumann ,OskerMorgensten.
2. Games and Decisions by R Duncann Lucie and Howard Riffa.

35
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code APPLIED ARTIFICIAL INTELLIGENCE L T P C

21D97301c 3 0 0 3
Semester III

Course Objectives:
• To understand several data science concepts using python..
• To understand Foundations of Natural Language Processing and Machine Learning.
• To design Supervised Learning Models.
• To Analyze the feature engineering concept.
Course Outcomes (CO): Student will be able to
• Understand several data science concepts using python..
• Understand Foundations of Natural Language Processing and Machine Learning.
• Design Supervised Learning Modles.
• Analyze the feature engineering concept.
UNIT - I Lecture Hrs:9
Fundamentals of programming: Python for data science- Introduction, Data Structures, Functions,
Numpy, Matplotlib.
UNIT - II Lecture Hrs:9
Data Science: Exploratory Data Analysis and Data Visualization- Plotting of Exploratory Data
Analysis(EDA), Linear Algebra, Probability and Statistics, Dimensionality Reduction and
Visualization, Principle Component Analysis(PCA), t-SNA(T- distributed Stochastic Neighborhood
Embedding .
UNIT - III Lecture Hrs:9
Foundations of Natural Language Processing and Machine Learning: Real world Problem- Predict
rating, given product reviews on Amazon, Classification and Regression Models- K nearest
Neighbors, Performance measurement of Models, Linear Regression, Logistic Regression, Solving
Optimization problems.
UNIT - IV Lecture Hrs:9
Machine Learning-II( Supervised Learning Models):Support Vector Machines, Decision Trees,
Ensemble Models.
UNIT - V Lecture Hrs:9
Feature Engineering-Product ionization and deployment of ML Models: Featurization and Feature
Engineering-Introduction, Moving window for time series data,Fourier Decomposition, Deep
Learning features- LSTM, CNN.
Textbooks:
1. Applied Artificial Intelligence- A handbook for business leaders by mariya yao, marlene jia,
Adelyn Zhou.
Reference Books:
1. Applied Artificial Intelligence by Professor Lewis Brown.
2. Applied Machine Learning by M.Gopal, A tata Mc Grawhill edition.
Online Learning Resources:
https://www.appliedaicourse.com/course/11/Applied-Machine-learning-course

36
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

AUDIT
COURSE-I

37
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code ENGLISH FOR RESEARCH PAPER WRITING L T P C

21DAC101a 2 0 0 0
Semester I

Course Objectives: This course will enable students:

 Understand the essentials of writing skills and their level of readability
 Learn about what to write in each section
 Ensure qualitative presentation with linguistic accuracy
Course Outcomes (CO): Student will be able to
 Understand the significance of writing skills and the level of readability
 Analyze and write title, abstract, different sections in research paper
 Develop the skills needed while writing a research paper
UNIT - I Lecture Hrs:10
1Overview of a Research Paper- Planning and Preparation- Word Order- Useful Phrases - Breaking
up Long Sentences-Structuring Paragraphs and Sentences-Being Concise and Removing Redundancy
-Avoiding Ambiguity
UNIT - II Lecture Hrs:10
Essential Components of a Research Paper- Abstracts- Building Hypothesis-Research Problem -
Highlight Findings- Hedging and Criticizing, Paraphrasing and Plagiarism, Cauterization
UNIT - III Lecture Hrs:10
Introducing Review of the Literature – Methodology - Analysis of the Data-Findings - Discussion-
Conclusions-Recommendations.

UNIT - IV Lecture Hrs:9

Key skills needed for writing a Title, Abstract, and Introduction
UNIT - V Lecture Hrs:9
Appropriate language to formulate Methodology, incorporate Results, put forth Arguments and draw
Conclusions
Suggested Reading
1. Goldbort R (2006) Writing for Science, Yale University Press (available on Google Books)
Model Curriculum of Engineering & Technology PG Courses [Volume-I]
2. Day R (2006) How to Write and Publish a Scientific Paper, Cambridge University Press
3. Highman N (1998), Handbook of Writing for the Mathematical Sciences, SIAM.
Highman’sbook
4. Adrian Wallwork , English for Writing Research Papers, Springer New York Dordrecht
Heidelberg London, 2011

38
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code L T P C
21DAC101b DISASTER MANAGEMENT 2 0 0 0
Semester I

Course Objectives: This course will enable students:

 Learn to demonstrate critical understanding of key concepts in disaster risk reduction
and humanitarian response.
 Critically evaluate disaster risk reduction and humanitarian response policy and practice from
Multiple perspectives.
 Developanunderstandingofstandardsofhumanitarianresponseandpracticalrelevanceinspecific types
of disasters and conflict situations
 Criticallyunderstandthestrengthsandweaknessesofdisastermanagementapproaches,planningand
programming in different countries, particularly their home country or the countries they work in
UNIT - I
Introduction:
Disaster:Definition,FactorsandSignificance;DifferenceBetweenHazardandDisaster;Naturaland
Manmade Disasters: Difference, Nature, Types and Magnitude.
Disaster Prone Areas in India:
Study of Seismic Zones; Areas Prone to Floods and Droughts, Landslides and Avalanches; Areas Prone
to Cyclonic and Coastal Hazards with Special Reference to Tsunami; Post- Disaster Diseases and
Epidemics
UNIT - II
Repercussions of Disasters and Hazards:
Economic Damage, Loss of Human and Animal Life, Destruction of Ecosystem. Natural Disasters:
Earthquakes,Volcanisms,Cyclones,Tsunamis,Floods,DroughtsandFamines,Landslides and Avalanches,
Man-made disaster: Nuclear Reactor Meltdown, Industrial Accidents, Oil Slicks and Spills, Outbreaks of
Disease and Epidemics, War and Conflicts.
UNIT - III
Disaster Preparedness and Management:
Preparedness: Monitoring of Phenomena Triggering ADisasteror Hazard; Evaluation of Risk:
Application of Remote Sensing, Data from Meteorological and Other Agencies, Media Reports:
Governmental and Community Preparedness.
UNIT - IV
Risk Assessment Disaster Risk:
Concept and Elements, Disaster Risk Reduction, Global and National Disaster Risk Situation.
TechniquesofRiskAssessment,GlobalCo-OperationinRiskAssessmentand Warning, People’s Participation
in Risk Assessment. Strategies for Survival.
UNIT - V
Disaster Mitigation:
Meaning,ConceptandStrategiesofDisasterMitigation,EmergingTrendsInMitigation.Structural
Mitigationand Non-Structural Mitigation, Programs of Disaster Mitigation in India.
Suggested Reading
1. R.Nishith,SinghAK,“DisasterManagementinIndia:Perspectives,issuesandstrategies
2. “’New Royal book
Company..Sahni,PardeepEt.Al.(Eds.),”DisasterMitigationExperiencesAndReflections”,PrenticeHa
39
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
ll OfIndia, New Delhi.
3. GoelS.L.,DisasterAdministrationAndManagementTextAndCaseStudies”,Deep&Deep
Publication Pvt. Ltd., New Delhi

40
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code SANSKRITFOR TECHNICAL KNOWLEDGE L T P C

21DAC101c 2 0 0 0
Semester I

Course Objectives: This course will enable students:

 To get a working knowledge in illustrious Sanskrit, the scientific language in the world
 Learning of Sanskrit to improve brain functioning
 LearningofSanskrittodevelopthelogicinmathematics,science&othersubjects enhancing the
memory power
 The engineering scholars equipped with Sanskrit will be able to explore the huge
 Knowledge from ancientliterature
Course Outcomes (CO): Student will be able to
 Understanding basic Sanskrit language
 Ancient Sanskrit literature about science &technology can be understood
 Being a logical language will help to develop logic in students
UNIT - I
Alphabets in Sanskrit,
UNIT - II
Past/Present/Future Tense, Simple Sentences
UNIT - III
Order, Introduction of roots
UNIT - IV
Technical information about Sanskrit Literature
UNIT - V
Technical concepts of Engineering-Electrical, Mechanical, Architecture, Mathematics
Suggested Reading
1.“Abhyaspustakam” –Dr.Vishwas, Sanskrit-Bharti Publication, New Delhi
2.“Teach Yourself Sanskrit ” Prat hama Deeksha- VempatiKutumbshastri, RashtriyaSanskrit
Sansthanam, New Delhi Publication
3.“India’s Glorious ScientificTradition” Suresh Soni, Ocean books (P) Ltd.,New Delhi

41
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

AUDIT
COURSE-II

42
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code L T P C
21DAC201a PEDAGOGY STUDIES 2 0 0 0
Semester II

Course Objectives: This course will enable students:

 Reviewexistingevidenceonthereviewtopictoinformprogrammedesignandpolicy making
undertaken by the DfID, other agencies and researchers.
 Identify critical evidence gaps to guide the development.
Course Outcomes (CO): Student will be able to
Students will be able to understand:
 Whatpedagogicalpracticesarebeingusedbyteachersinformalandinformalclassrooms in developing
countries?
 What is the evidence on the effectiveness of these pedagogical practices, in what
conditions, and with what population of learners?
 Howcanteachereducation(curriculumandpracticum)andtheschoolcurriculumand guidance
materials best support effective pedagogy?
UNIT - I
Introduction and Methodology: Aims and rationale, Policy back ground, Conceptual frame work and
terminology Theories oflearning,Curriculum,Teachereducation.Conceptualframework,Research
questions. Overview of methodology and Searching.
UNIT - II
Thematic overview: Pedagogical practices are being used by teachers in formal and informal
classrooms in developing countries. Curriculum, Teacher education.
UNIT - III
Evidence on theeffectivenessofpedagogicalpractices,Methodologyfortheindepthstage:quality assessmen t
of included studies. How can teacher education (curriculumandpracticum) andthescho curriculum and
guidance materials best support effective pedagogy? Theory of change. Strength and nature of th body of
evidence for effective pedagogical practices. Pedagogic theory and pedagogical approaches. Teachers’
attitudes and beliefs and Pedagogic strategies.
UNIT - IV
Professional development: alignment with classroom practices and follow-up support, Peer support,
Support from the head
teacherandthecommunity.Curriculumandassessment,Barrierstolearning:limitedresourcesand large class
sizes
UNIT - V
Researchgapsandfuturedirections:Researchdesign,Contexts,Pedagogy,Teachereducation,
Curriculum and assessment, Dissemination and research impact.
Suggested Reading
1. AckersJ,HardmanF(2001)ClassroominteractioninKenyanprimaryschools,Compare,
31 (2): 245-261.
2. AgrawalM(2004)Curricularreforminschools:Theimportanceofevaluation,Journalof
3. Curriculum Studies, 36 (3): 361-379.
4. AkyeampongK(2003) Teacher training in Ghana - does it count? Multi-site teachereducation
research project (MUSTER) country report 1. London: DFID.
5. Akyeampong K, LussierK, PryorJ, Westbrook J (2013)Improving teaching and learning of basic
maths and reading in Africa: Does teacherpreparation count?International Journal Educational
Development, 33 (3): 272–282.
43
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI
6. Alexander RJ(2001) Culture and pedagogy: International comparisons in primary education.
Oxford and Boston: Blackwell.
Chavan M (2003)ReadIndia: A mass scale, rapid, ‘learning to read’campaign.
7. www.pratham.org/images/resource%20working%20paper%202.pdf.

44
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code L T P C
21DAC201b STRESSMANAGEMENT BY YOGA 2 0 0 0
Semester II

Course Objectives: This course will enable students:

 To achieve overall health of body and mind
 To overcome stres
Course Outcomes (CO): Student will be able to
 Develop healthy mind in a healthy body thus improving social health also
 Improve efficiency
UNIT - I
Definitions of Eight parts of yog.(Ashtanga)
UNIT - II
Yam and Niyam.
UNIT - III
Do`sand Don’t’sin life.
i) Ahinsa,satya,astheya,bramhacharyaand aparigrahaii)
Shaucha,santosh,tapa,swadhyay,ishwarpranidhan
UNIT - IV
Asan and Pranayam
UNIT - V
i)Variousyogposesand theirbenefitsformind &body
ii)Regularizationofbreathingtechniques and its effects-Types ofpranayam
Suggested Reading
1.‘Yogic Asanas forGroupTarining-Part-I”: Janardan SwamiYogabhyasiMandal, Nagpur
2.“Rajayogaor conquering the Internal Nature” by Swami Vivekananda, Advaita
Ashrama (Publication Department), Kolkata

45
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code PERSONALITY DEVELOPMENT THROUGHLIFE L T P C

21DAC201c ENLIGHTENMENTSKILLS 2 0 0 0
Semester II

Course Objectives: This course will enable students:

 To learn to achieve the highest goal happily
 To become a person with stable mind, pleasing personality and determination
 To awaken wisdom in students
Course Outcomes (CO): Student will be able to
 StudyofShrimad-Bhagwad-Geetawillhelpthestudentindevelopinghispersonalityand achieve
the highest goal in life
 The person who has studied Geetawilllead the nation and mankind to peace and prosperity
 Study of Neetishatakam will help in developing versatile personality of students
UNIT - I
Neetisatakam- Holistic development of personality
Verses-19,20,21,22(wisdom)
Verses-29,31,32(pride &heroism)
Verses-26,28,63,65(virtue)
UNIT - II
Neetisatakam- Holistic development of personality
Verses-52,53,59(dont’s)
Verses-71,73,75,78(do’s)
UNIT - III
Approach to day to day work and duties.
ShrimadBhagwadGeeta:Chapter2-Verses41,47,48,
Chapter3-Verses13,21,27,35,Chapter6-Verses5,13,17,23,35,
Chapter18-Verses45,46,48.
UNIT - IV
Statements of basic knowledge.
ShrimadBhagwadGeeta:Chapter2-Verses 56,62,68
Chapter12 -Verses13,14,15,16,17,18
Personality of Rolemodel. Shrimad Bhagwad Geeta:
UNIT - V
Chapter2-Verses 17,Chapter3-Verses36,37,42,
Chapter4-Verses18,38,39
Chapter18– Verses37,38,63
Suggested Reading
1.“SrimadBhagavadGita”bySwamiSwarupanandaAdvaitaAshram(PublicationDepartment),
Kolkata
2.Bhartrihari’sThree Satakam (Niti-sringar-vairagya) by P.Gopinath, RashtriyaSanskrit
Sansthanam, New Delhi.

46
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

OPEN
ELECTIVE

47
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code INDUSTRIAL SAFETY L T P C

21DOE301b (Common to M.Tech CSE, CN, SE,AI & ML) 3 0 0 3
Semester III

Course Objectives:
• To know about Industrial safety programs and toxicology, Industrial laws , regulations and source
models
• To understand about fire and explosion, preventive methods, relief and its sizing methods
• To analyse industrial hazards and its risk assessment.
Course Outcomes (CO): Student will be able to
• To list out important legislations related to health, Safety and Environment.
• To list out requirements mentioned in factories act for the prevention of accidents.
• To understand the health and welfare provisions given in factories act.
UNIT - I Lecture Hrs:
Industrial safety: Accident, causes, types, results and control, mechanical and electrical hazards, types, causes
and preventive steps/procedure, describe salient points of factories act 1948 for health and safety, wash rooms,
drinking water layouts, light, cleanliness, fire, guarding, pressure vessels, etc, Safety color codes. Fire
prevention and firefighting, equipment and methods.
UNIT - II Lecture Hrs:
Fundamentals of maintenance engineering: Definition and aim of maintenance engineering, Primary and
secondary functions and responsibility of maintenance department, Types of maintenance, Types and
applications of tools used for maintenance, Maintenance cost & its relation with replacement economy, Service
life of equipment.
UNIT - III Lecture Hrs:
Wear and Corrosion and their prevention: Wear- types, causes, effects, wear reduction methods, lubricants-
types and applications, Lubrication methods, general sketch, working andapplications, i. Screw down grease
cup, ii. Pressure grease gun, iii. Splash lubrication, iv. Gravity lubrication, v. Wick feed lubrication vi. Side
feed lubrication, vii. Ring lubrication, Definition, principle and factors affecting the corrosion. Types of
corrosion, corrosion prevention methods.
UNIT - IV Lecture Hrs:
Fault tracing: Fault tracing-concept and importance, decision treeconcept, need and applications, sequence of
fault finding activities, show as decision tree, draw decision tree for problems in machine tools, hydraulic,
pneumatic, automotive, thermal and electrical equipment’s like, I. Any one machine tool, ii. Pump iii. Air
compressor, iv. Internal combustion engine, v. Boiler, vi. Electrical motors, Types of faults in machine tools
and their general causes.
UNIT - V Lecture Hrs:
Periodic and preventive maintenance: Periodic inspection-concept and need, degreasing, cleaning and repairing
schemes, overhauling of mechanical components, overhauling of electrical motor, common troubles and
remedies of electric motor, repair complexities and its use, definition, need, steps and advantages of preventive
maintenance. Steps/procedure for periodic and preventive maintenance of: I. Machine tools, ii. Pumps, iii. Air
compressors, iv. Diesel generating (DG) sets, Program and schedule of preventive maintenance of mechanical
and electrical equipment, advantages of preventive maintenance. Repair cycle concept and importance
Textbooks:
1. Maintenance Engineering Handbook, Higgins & Morrow, Da Information Services.
2. Maintenance Engineering, H. P. Garg, S. Chand and Company.
Reference Books:
1.Pump-hydraulic Compressors, Audels, Mcgrew Hill Publication.
2. Foundation Engineering Handbook, Winterkorn, Hans, Chapman & Hall London.

48
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code BUSINESS ANALYTICS L T P C

21DOE301c (Common to M.Tech CSE, CN, SE,AI & ML) 3 0 0 3
Semester III

Course Objectives:
• The main objective of this course is to give the student a comprehensive understanding of
business analytics methods.
Course Outcomes (CO): Student will be able to
• Students will demonstrate knowledge of data analytics.
• Students will demonstrate the ability of think critically in making decisions based on
data and deep analytics.
• Students will demonstrate the ability to use technical skills in predicative and
prescriptive modeling to support business decision-making.
• Students will demonstrate the ability to translate data into clear, actionable insights.
UNIT - I Lecture Hrs:
Business Analysis: Overview of Business Analysis, Overview of Requirements, Role of the Business Analyst.
Stakeholders: the project team, management, and the front line, Handling Stakeholder Conflicts.
UNIT - II Lecture Hrs:
Life Cycles: Systems Development Life Cycles, Project Life Cycles, Product Life Cycles, Requirement Life
Cycles.
UNIT - III Lecture Hrs:
Forming Requirements: Overview of Requirements, Attributes of Good Requirements, Types of Requirements,
Requirement Sources, Gathering Requirements from Stakeholders, Common Requirements Documents.
Transforming Requirements: Stakeholder Needs Analysis, Decomposition Analysis, Additive/Subtractive
Analysis, Gap Analysis, Notations (UML & BPMN), Flowcharts, Swim Lane Flowcharts, Entity-Relationship
Diagrams, State-Transition Diagrams, Data Flow Diagrams, Use Case Modeling, Business Process Modeling
UNIT - IV Lecture Hrs:
Finalizing Requirements: Presenting Requirements, Socializing Requirements and Gaining Acceptance,
Prioritizing Requirements. Managing Requirements Assets: Change Control, Requirements Tools
UNIT - V Lecture Hrs:
Recent Trands in: Embedded and colleborative business intelligence, Visual data recovery, Data Storytelling
and Data Journalism.
Textbooks:
1. Business Analysis by James Cadle et al.
2. Project Management: The Managerial Process by Erik Larson and, Clifford Gray
Reference Books:
1. Business analytics Principles, Concepts, and Applications by Marc J. Schniederjans, Dara G.
Schniederjans, Christopher M. Starkey, Pearson FT Press.
2. Business Analytics by James Evans, persons Education.

49
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

Course Code OPTIMIZATION TECHNIQUES L T P C

21DOE301f (Common to M.Tech CSE, CN, SE,AI & ML) 3 0 0 3
Semester III

Course Objectives:
• Enumerate the fundamental knowledge of Linear Programming and Dynamic
Programming problems.
• Learn classical optimization techniques and numerical methods of optimization.
• Know the basics of different evolutionary algorithms.
• Explain Integer programming techniques and apply different optimization
techniques to solve various models arising from engineering areas.
Course Outcomes (CO): Student will be able to
• Explain the fundamental knowledge of Linear Programming and Dynamic
Programming problems.
• Use classical optimization techniques and numerical methods of optimization.
• Describe the basics of different evolutionary algorithms.
• Enumerate fundamentals of Integer programming technique and apply different
techniques to solve various optimization problems arising from engineering areas
UNIT - I Lecture Hrs:
LINER PROGRAMMING (L.P):
Revised Simplex Method, Duel simplex Method, Sensitivity Analysis
DYNAMIC PROGRAMMING (D.P):
Multistage decision processes. Concepts of sub optimization, Recursive Relation-calculus method, tabular
method, LP as a case of D.P.
UNIT - II Lecture Hrs:
CLASSICAL OPTIMIZATION TECHNIQUES:
Single variable optimization without constraints, Multi variable optimization without constraints, multivariable
optimization with constraints – method of Lagrange multipliers, Kuhn-Tucker conditions.
NUMERICAL METHODS FOR OPTIMIZATION:
Nelder Mead’s Simplex search method, Gradient of a function, Steepest descent method, Newton’s method
UNIT - III Lecture Hrs:
MODERN METHODS OF OPTIMIZATION:
GENETIC ALGORITHM (GA):
Differences and similarities between conventional and evolutionary algorithms, working principle, Genetic
Operators- reproduction, crossover, mutation
GENETIC PROGRAMMING (GP):
Principles of genetic programming, terminal sets, functional sets, differences between GA &GP, Random
population generation. Fuzzy Systems: Fuzzy set Theory, Optimization of Fuzzy systems
UNIT - IV Lecture Hrs:
INTEGER PROGRAMMING:
Graphical Representation, Gomory’s Cutting Plane Method,Balas’ Algorithm for Zero–One Programming,
Branch-and-Bound Method
UNIT - V Lecture Hrs:
APPLICATIONS OF OPTIMIZATION IN DESIGN AND MANUFACTURING SYSTEMS:
Formulation of model- optimization of path synthesis of a four-bar mechanism, minimization of weight of a
cantilever beam, general optimization model of a machining process, optimization of arc welding parameters,
and general procedure in optimizing machining operations sequence.
Textbooks:
1. Engineering Optimization (4th Edition) by S.S.Rao, New Age International,
Reference Books:

50
 R21 Regulations

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

(Established by Govt. of A.P., ACT No.30 of 2008)
ANANTHAPURAMU – 515 002 (A.P) INDIA
M.TECH. IN ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
COURSE STRUCTURE & SYLLABI

1. Optimization for Engineering Design by Kalyanmoy Deb, PHI Publishers

2. Genetic algorithms in Search, Optimization, and Machine learning – D.E.Goldberg,
Addison-Wesley Publishers
3. Operations Research by Hillar and Liberman, TMH Publishers
4. Optimal design – JasbirArora, McGraw Hill (International) Publisher

51