Maulana Abul Kalam Azad University of Technology, West Bengal

(Formerly West Bengal University of Technology)

Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

SEMESTER – VI

Machine learning Applications

Code: PCC- AIML601
Contacts: 2L

Name of the Course: Machine learning Applications

Course Code: PCC- AIML601 Semester: VI
Duration: 6 months Maximum Marks:100
Teaching Scheme Examination Scheme
Theory:2 hrs./week Mid Semester exam: 15
Tutorial: NIL Assignment and Quiz: 10 marks
Attendance : 5 marks
Practical: NIL End Semester Exam :70 Marks
Credit Points: 2

 Introduction to linear regression (and multivariate linear regression)

 Logistic Regression and regularization

 Practical aspects of implementation

 Decision trees and pruning, implementation of decision trees

 Support vector machines and making them work in practice

 Boosting - implementing different boosting methods with decision trees.

 Using the algorithms for several tasks - how to set up the problem, debug, select
features and develop the learning algorithm.

 Unsupervised learning - k-means, PCA, hierarchical clustering.

 Implementing the clustering algorithms

 Parallelizing the learning algorithms

 Applications

 Choosing from multiple algorithms - What will work?

1
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Machine learning Applications Lab

Code: PCC- AIML 691
Contacts: 4P

Name of the Course: Machine learning Applications Lab

Course Code: PCC- AIML 691 Semester: VI

Duration:6 months Maximum Marks:100

Teaching Scheme:
Theory: hrs./week Continuous Internal Assessment
Tutorial: NIL External Assesement:60
Practical: 4 hrs./week Distribution of marks:40
Credit Points: 2

1. Explore visualization features of the tool for analysis and WEKA.

2. Perform data preprocessing tasks and Demonstrate performing association rule mining on data sets
3. Demonstrate performing classification on data sets
4. Demonstrate performing clustering on data sets
5. Sample Programs using German Credit Data
6. One approach for solving the problem encountered in the previous question is using cross-validation? Describe
what is cross validation briefly. Train a decision tree again using cross validation and report your results. Does
accuracy increase/decrease? Why?
7. Check to see if the data shows a bias against “foreign workers” or “personal-status”.. Did removing these attributes
have any significantly effect? Discuss
8. Another question might be, do you really need to input so many attributes to get good results? Try out some
combinations.
9. Train your decision tree and report the Decision Tree and cross validation results. Are they significantly different
from results obtained in problem 6
10. How does the complexity of a Decision Tree relate to the bias of the model?
11. One approach is to use Reduced Error Pruning. Explain this idea briefly. Try reduced error pruning for training
your Decision Trees using cross validation and report the Decision Trees you obtain? Also Report your accuracy
using the pruned model Does your Accuracy increase?
12.How Can you Convert Decision Tree in to “If then else Rules”.Make Up your own Small Decision Tree consisting
2-3 levels and convert into a set of rules. Report the rule obtained by training a one R classifier. Rank the performance
of j48,PART,oneR.

2
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Subject: Deep Learning

Course Code: PCCAIML 602 Semester: VI
Duration: 36 Hrs. Maximum Marks: 100

Teaching Scheme Examination Scheme

Theory: 3 hrs./week End Semester Exam: 70

Tutorial: 0 Attendance : 5

Practical: Continuous Assessment:25

Credit: 3

Aim:

Sl. No.

1. To improve the performance of a Deep Learning model

2. to the reduce the optimization function which could be divided based on the classificationand
the regression problems

Objective:

Sl. No.

1. To acquire knowledge on the basics of neural networks.

2. To implement neural networks using computational tools for variety of problems.

3. To explore various deep learning algorithms.

Pre-Requisite:

Sl. No.

1. Calculus, Linear Algebra

2. Probability & Statistics

3. Ability to code in R/Python

Contents Hrs./week

Chapter Name of the Topic Hours Marks

3
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

01 Introduction 3 5

Various paradigms of earning problems, Perspectives and Issues in

deep learning framework, review of fundamental learning
techniques.
02 6 10
Feed forward neural network

Artificial Neural Network, activation function, multi-layer neural

network, cardinality, operations, and properties of fuzzy relations.
03 Training Neural Network 6 15

Risk minimization, loss function, backpropagation, regularization,

model selection, and optimization.
04 Conditional Random Fields 9 15

Linear chain, partition function, Markov network, Belief

propagation, Training CRFs, Hidden Markov Model, Entropy.
05 Deep Learning 6 15

Deep Feed Forward network, regularizations, training deep

models, dropouts, Convolutional Neural Network, Recurrent
Neural Network, Deep Belief Network.
06 Deep Learning research 6 10

Object recognition, sparse coding, computer vision, natural

language
Sub Total: 36 70
Internal Assessment Examination & Preparation of Semester 4 30
Examination
Total: 40 100
List of Books
Text Books:

Name of Author Title of the Book Edition/ISSN/ISBN Name of the Publisher

Rajiv Chopra Dep Learning First Edition Khanna Book

(AICTE Recommended Publishing
Textbook)

Goodfellow, Deep Learning MIT Press

I.,Bengio,Y.,
andCourville
A.,
Satish Kumar Neural Networks: A Tata McGraw-Hill
Classroom Approach

Reference Books:

4
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Bishop, C. ,M. Pattern Recognition and Springer

Machine Learning

Yegnanarayana, B. Artificial PHI Learning Pvt. Ltd

Neural
Networks
Golub, G.,H., and Matrix Computations JHU Press
VanLoan,C.,F.

Soft Computing
Code: PECAIML603 & PECAIML693
Contacts: 3L + 4P

Name of the Course: Soft Computing

Course Code: PECAIML603 & Semester: VI
PECAIML693
Duration:6 months Maximum Marks: 100
Teaching Scheme Examination Scheme
Theory: 3 hrs./week Mid Semester exam: 15
Tutorial: NIL Assignment and Quiz : 10 marks
Attendance: 5 marks
Practical: 4 hrs./week End Semester Exam: 70 Marks
Practical Sessional internal continuous
evaluation:40
Practical Sessional external examination: 60
Credit Points: 3+2
Unit Content Hrs/U Marks/Unit
nit
Introduction: Introduction to soft computing;
1 introduction to fuzzy sets and fuzzy logic systems; 8
introduction to biological and artificial neural
network; introduction to Genetic Algorithm

5
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Fuzzy sets and Fuzzy logic systems: 10

2 Classical Sets and Fuzzy Sets and Fuzzy relations :
Operations on Classical sets, properties of classical
sets, Fuzzy set operations, properties of fuzzy sets,
cardinality, operations, and properties of fuzzy
relations.
Membership functions : Features of membership
functions, standard forms and boundaries, different
fuzzification methods.
Fuzzy to Crisp conversions: Lambda Cuts for fuzzy
sets, fuzzy Relations, Defuzzification methods.
Classical Logic and Fuzzy Logic: Classical predicate
logic, Fuzzy Logic, Approximate reasoning and Fuzzy
Implication Fuzzy Rule based Systems: Linguistic
Hedges, Fuzzy Rule based system – Aggregation of
fuzzy Rules, Fuzzy Inference System- Mamdani Fuzzy
Models – Sugeno Fuzzy Models.
Applications of Fuzzy Logic: How Fuzzy Logic is
applied in Home Appliances, General Fuzzy Logic
controllers, Basic Medical Diagnostic systems and
Weather forecasting

Neural Network 10
3 Introduction to Neural Networks: Advent of Modern
Neuroscience, Classical AI and Neural Networks,
Biological Neurons and Artificial neural network; model
of artificial neuron.
Learning Methods : Hebbian, competitive, Boltzman etc.,
Neural Network models: Perceptron, Adaline andMadaline
networks; single layer network; Back- propagation and
multi layer networks.
Competitive learning networks: Kohonen self
organizing networks, Hebbian learning; Hopfield
Networks. Neuo-Fuzzy modelling:Applications of
Neural Networks: Pattern Recognition and
classification
Genetic Algorithms: Simple GA, crossover and mutation, 10
4. Multi-objective Genetic Algorithm (MOGA).
Applications of Genetic Algorithm: geneticalgorithms in
search and optimization, GA based
clustering Algorithm, Image processing and pattern
Recognition
5 PSO:Other Soft Computing techniques: 4
Simulated Annealing, Tabu search, Ant
colony optimization (ACO), Particle Swarm
Optimization (PSO).

6
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Practical:

Skills to be developed:

1. Able to apply Soft Computing techniques to solve a number of real life problems.

Assignments: : Assignment from theory

List of Books

Text Books:

Name of Author Title of the Book Edition/ISSN/ISBN Name of the Publisher

Timothy J. Ross, Fuzzy logic with

JohnWiley and Sons engineering applications

S. Rajasekaran Neural Networks, Fuzzy PHI

andG.A.V.Pai Logic and Genetic
Algorithms
S N Sivanandam, Principles of Soft
S.Sumathi, John Computing

Reference Books:
George J. Klir and Fuzzy Sets and Fuzzy Prentice Hall
BoYuan Logic: Theory and
Applications
Simon Haykin Neural Networks: A Prentice Hall.
Comprehensive
Foundation
End Semester Examination Scheme. Maximum Marks-70. Time allotted-3hrs.

Group Unit Objective Questions Subjective Questions

(MCQ only with the
correct answer)
No of Total No of To answer Marks per Total
question to Marks question to question Marks
be set be set
A ALL 10 5 3 15

10 70

B All

c All 5 3 45

● Only multiple choice type question (MCQ) with one correct answer are to be set in the objectivepart.
● Specific instruction to the students to maintain the order in answering objective questions should be
given on top of the question paper.
Examination Scheme for end semester examination:

7
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Group Chapter Marks of each Question to be Question to be

question set answered

A ALL 1 10 10

B ALL 5 5 3

C ALL 15 5 3

Examination Scheme for Practical Sessional examination:

Practical Internal Sessional Continuous Evaluation
Internal Examination:
Continuous evaluation 40
External Examination: Examiner-
Signed Lab Assignments 10
On Spot Experiment 40
Viva voce 10 60

Name of the Course: Computer Networks

Course Code: PCC-CS602 Semester: VI

Duration:6 months Maximum Marks:100
Teaching Scheme Examination Scheme

Theory:3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz: 10 marks
Attendance: 5 marks
Practical: hrs./week End Semester Exam:70 Marks
Credit Points: 3
Objective:
1 To develop an understanding of modern network architectures from a design and
performance perspective.
2 To introduce the student to the major concepts involved in wide-area networks
(WANs), local area networks (LANs) and Wireless LANs (WLANs).
3 To provide an opportunity to do network programming
4 To provide a WLAN measurement ideas.
Unit Content Hrs/Unit Marks/Unit

8
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Data communication Components:

1 Representation of data and its flow 9
Networks,Various Connection Topology,
Protocols and Standards, OSI model,
Transmission Media, LAN: Wired LAN,
Wireless LANs, Connecting LAN and Virtual
LAN, Techniques for Bandwidth utilization:
Multiplexing - Frequency division, Time
division and Wave division, Concepts on
spread spectrum.
Data Link Layer and Medium Access Sub 8
2 Layer: Error Detection and Error Correction -
Fundamentals, Block coding, Hamming
Distance, CRC; Flow Control and Error control
protocols - Stop and Wait, Go back –
N ARQ, Selective Repeat ARQ, Sliding
Window, Piggybacking,
Random Access, Multiple access protocols -
Pure ALOHA, Slotted
ALOHA,CSMA/CD,CDMA/CA
Network Layer: Switching, Logical addressing 14
3 – IPV4, IPV6; Address mapping – ARP,
RARP, BOOTP and DHCP–Delivery,
Forwarding and Unicast Routing protocols.
Transport Layer: Process to Process 8
4. Communication, User Datagram Protocol
(UDP), Transmission Control Protocol (TCP),
SCTP Congestion Control; Quality of Service,
QoS improving techniques: Leaky Bucket and
Token Bucket algorithm.
5 Application Layer: Domain Name Space 8
(DNS), DDNS, TELNET,
EMAIL, File Transfer Protocol (FTP), WWW,
HTTP, SNMP, Bluetooth, Firewalls, Basic
concepts of Cryptography.
Text book and Reference books:
1. Introduction to Algorithms" by Cormen, Leiserson, Rivest, Stein.
2. "The Design and Analysis of Computer Algorithms" by Aho, Hopcroft, Ullman.
3. "Algorithm Design" by Kleinberg and Tardos.
4. Design & Analysis of Algorithms, Gajendra Sharma, Khanna Publishing House, New Delhi

Course Outcomes:

On completion of the course students will be able to

1. Understand research problem formulation.
2. Analyze research related information
3. Follow research ethics
4. Understand that today’s world is controlled by Computer, Information Technology, but tomorrow
9
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

world will be ruled by ideas, concept, and creativity.

5. 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.
6. 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.

10
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Computer Networks Lab

Code: PCC-CS692
Contacts: 4P

Name of the Course: Computer Networks Lab

Course Code: PCC- Semester: VI

CS692

Duration:6 months Maximum Marks:100

Teaching Scheme:
Theory: hrs./week Continuous Internal Assessment
Tutorial: NIL External Assesement:60
Practical: 4 hrs./week Distribution of marks:40
Credit Points: 2

1) NIC Installation & Configuration (Windows/Linux)

2) Understanding IP address, subnet etc
Familiarization with
 Networking cables (CAT5, UTP)
 Connectors (RJ45, T-connector)
 Hubs, Switches
3) TCP/UDP Socket Programming
 Simple, TCP based, UDP based
 Multicast & Broadcast Sockets
 Implementation of a Prototype Multithreaded Server
4) Implementation of
  Data Link Layer Flow Control Mechanism (Stop & Wait, Sliding Window)
  Data Link Layer Error Detection Mechanism (Cyclic Redundancy Check)
  Data Link Layer Error Control Mechanism (Selective Repeat, Go Back N)
5) Server Setup/Configuration
FTP, TelNet, NFS, DNS, Firewall

Any experiment specially designed by the college

(Detailed instructions for Laboratory Manual to be followed for further guidance)

11
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Big Data Analytics

Code: PECAIML601A
Contacts: 3L

Name of the Course: Big Data Analytics

Course Code: Semester: VI

PECAIML601A
Duration:6 months Maximum Marks: 100
Teaching Scheme Examination Scheme

Theory: 3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz : 10 marks
Attendance: 5 marks
Practical: NIL End Semester Exam: 70 Marks
Credit Points: 3
NO. OF
LECTURE WITH BREAKUP
LECTUR
Unit 1:
What is big data, why big data, convergence of key trends, unstructured data,
industry examples of big data, web analytics, big data and marketing, fraud and
big data, risk and big data, credit risk management, big data and algorithmic 8
trading, big data and healthcare, big data in medicine, advertising and big data,
big data technologies, introduction to Hadoop, open source technologies, cloud
and big data, mobile business intelligence, Crowd sourcing analytics, inter and
trans firewall analytics.
Unit 2:
Introduction to NoSQL, aggregate data models, aggregates, key-value and
document data models, relationships, graph databases, schemaless databases,
materialized views, distribution models, sharding, master-slave replication, peer- 8
peer replication, sharding and replication, consistency, relaxing consistency,
version stamps, map-reduce, partitioning and combining, composing map-reduce
calculations.
Unit 3:
Data format, analyzing data with Hadoop, scaling out, Hadoop streaming, Hadoop
pipes, design of Hadoop distributed file system (HDFS), HDFS concepts, Java 9
interface, data flow, Hadoop I/O, data integrity, compression, serialization, Avro,
file-based datastructures
Unit 4:
MapReduce workflows, unit tests with MRUnit, test data and local tests, anatomy
of MapReduce job run, classic Map-reduce, YARN, failures in classic Map-reduce 10
and YARN, job scheduling, shuffle and sort, task execution,
MapReduce types, input formats, output formats
Unit 5: 7
Hbase, data model and implementations, Hbase clients, Hbase
examples, praxis.Cassandra, Cassandra data model, Cassandra examples,
Cassandra clients, Hadoop integration.

12
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Unit 6:
Pig, Grunt, pig data model, Pig Latin, developing and testing Pig Latin scripts. 6
Hive, data types and file formats, HiveQL data definition, HiveQL data
manipulation, HiveQL queries.

References:
1. Michael Minelli, Michelle Chambers, and AmbigaDhiraj, "Big Data, Big Analytics: Emerging
2. V.K. Jain, Big Data and Hadoop, Khanna Publishing House, New Delhi (2017).
3. V.K. Jain, Data Analysis, Khanna Publishing House, New Delhi (2019).
4. Business Intelligence and Analytic Trends for Today's Businesses", Wiley, 2013.
5. P. J. Sadalage and M. Fowler, "NoSQL Distilled: A Brief Guide to the Emerging
World of Polyglot Persistence", Addison-Wesley Professional, 2012.
6. Tom White, "Hadoop: The Definitive Guide", Third Edition, O'Reilley, 2012.
7. Eric Sammer, "Hadoop Operations", O'Reilley, 2012.
8. E. Capriolo, D. Wampler, and J. Rutherglen, "Programming Hive", O'Reilley, 2012.
9. Lars George, "HBase: The Definitive Guide", O'Reilley, 2011.
10. Eben Hewitt, "Cassandra: The Definitive Guide", O'Reilley, 2010.
11. Alan Gates, "Programming Pig", O'Reilley, 2011.

13
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Distributed Systems
Code: PECAIML-601C
Contact: 3L

Unit Content Hrs/Unit Marks/Unit

INTRODUCTION
1 Distributed data processing; What is a DDBS; 8
Advantages and disadvantages of DDBS; Problem
areas; Overview of database and computer network
concepts DISTRIBUTED DATABASE
MANAGEMENT SYSTEM ARCHITECTURE
Transparencies in a distributed DBMS; Distributed
DBMS architecture; Global directory issues
DISTRIBUTED DATABASE 11
2 DESIGN
Alternative design strategies;
Distributed design issues;
Fragmentation; Data allocation
SEMANTICS DATA CONTROL
View management; Data security;
Semantic Integrity Control QUERY
PROCESSING ISSUES
Objectives of query processing;
Characterization of query processors;
Layers of query processing; Query
decomposition; Localization of
distributed data
DISTRIBUTED QUERY OPTIMIZATION 11
3 Factors governing query optimization; Centralized
query optimization; Ordering of fragment queries;
Distributed query optimization algorithms
TRANSACTION MANAGEMENT
The transaction concept; Goals of transaction
management; Characteristics of transactions;
Taxonomy of transaction models
CONCURRENCY CONTROL
Concurrency control in centralized database systems;
Concurrency control in DDBSs; Distributed
concurrency control algorithms; Deadlock
management
Reliability issues in DDBSs; Types of failures; 8
4. Reliability techniques; Commit protocols; Recovery
protocols Algorithm
5 PARALLEL DATABASE SYSTEMS 6
Parallel architectures; parallel query
processing and

14
PG
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

6 ADVANCED TOPICS Mobile 4

Databases, Distributed Object
Management, Multi-databases

Text book and Reference books:

1. Principles of Distributed Database Systems, M.T. Ozsu and PValduriez,
Prentice-Hall, 1991.
2. Distributed Database Systems, D. Bell and J. Grimson, Addison-
Wesley, 1992.

Data Mining
Code: PECAIML-601B
Contacts: 3L

Name of the Course: Data Mining

Course Code PEC- Semester: VI

AIML601B
Duration: 6 months Maximum Marks: 100
Teaching Scheme Examination Scheme

Theory:3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz: 10 marks
Attendance: 5 marks
Practical: NIL End Semester Exam:70 Marks
Credit Points: 3

Unit Content Hrs/Unit Marks/Unit

Unit 1:
1 Overiew of data ming and predictive analytics. Where 4
does it apply and where does it not apply. The emerging
interdisplinary field of Data Science – what on Earth is
it? The potential pitfalls of analytics including big bad
data and the problem of local sparsity in large data sets -
- big never guarantees sufficient. Brief discussion of
Career Opportunities including an overview of the UNH
MS Analytics program.
Unit 2:
2 Data preprocessing and cleanup 3
including informative missing values
and imputation.

15
PG
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Unit 3:
3 Unsupervised learning: Exploring data with 8
visualization (primarily JMP Pro and Enterprise Guide),
Principal Components, Cluster Analysis, Variables
Clustering, and Market Basket analysis (association
analysis). The problem of explanatory (traditional) vs
predictive modeling and why it matters.
Unit 4:
4. The under and overfitting dilemma of 6
predictive modeling. Includes a discussion
of measures of overfitting and underfitting
such as AICc, BIC, and the very new ERIC.
5 Unit 5: 2
Validation strategies to assess model predictive behavior
and predictive inference
6 Unit 6: 5
Supervised learning for classification: k-nearest neighbors,
Decision Trees and Random Forests, Naïve Bayes, Neural Nets,
Logistic Regression, Generalized Regression, Support Vector
Machines, Discriminant Analysis. Topics include boosted
neural and tree models.

7 Unit 7: 6
Supervised learning for prediction: review of multiple
linear regression and related topics like influence and
multi-collinearity, PCR, Neural Nets, Generalized
Regression including the LASSO (adaptive), LARS,
Ridge, and Elastic Net (adaptive). Traditional variable
Selection strategies such as Forward Selection and All
Possible Models will also be covered.
8 Unit 8: 6
Model assessment measures for predictive and
classification models: model scoring, prediction error
analysis, ROC and Lift curves, profit matrices for

16
PG
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

classification, various model comparison criteria.

Ensemble Modeling: combining predictive models to
create even more powerful models; includes boosting
and bagging strategies.

Text book and Reference books:

1. Data Mining for Business Intelligence: Concepts, Techniques and Applications with JMP Pro;
Shmueli, Bruce, Stephens, Patel 2017,Wiley & Sons
2. Preparing Data for Analysis with JMP by Robert Carver
3. Introduction to Statistical Learing, sixth printing, by Gareth, Tibshirani, Hastie, and Whitten

Database Management Systems

Code: OECAIML-601A
Contact: 3L

Name of the Course: Database Management Systems

Course Code: OECAIML-601A Semester: VI

Duration:6 months Maximum Marks:100
Teaching Scheme Examination Scheme

Theory:3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz: 10 marks
Attendance: 5 marks
Practical: hrs./week End Semester Exam:70 Marks
Credit Points: 3

Unit Content Hrs/Unit Marks/Unit

Database system architecture:Data
1 Abstraction, Data Independence,Data 9
Definition Language(DDL),Data
ManipulationLanguage(DML).
Data models: Entity-relationshipmodel,
network model, relational and object oriented
data models, integrity constraints, data
manipulation operations.

17
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Relational query languages: Relational algebra, 13

2 Tuple and domain relational calculus, SQL3,
DDL and DML constructs, Open source and
Commercial DBMS - MYSQL, ORACLE, DB2,
SQLserver.
Relational database design: Domain
and data dependency,
Armstrong’s axioms, Normal forms,
Dependency preservation, Losslessdesign.
Query processing and optimization:
Evaluation of relational algebra
expressions,Query equivalence, Join
strategies, Query optimization
algorithms.
3 Storage strategies: Indices, B-trees, hashing. 3
Transaction processing: Concurrencycontrol, 5
4. ACID property, Serializability of scheduling,
Locking and timestamp based schedulers, Multi-
version and optimistic Concurrency Control
schemes, Database recovery.
5 Database Security: Authentication, 3
Authorization and access control, DAC,MAC and
RBAC models, Intrusion detection, SQL
injection.
6 Advanced topics: Object oriented and object 3
relational databases, Logical databases, Web
databases, Distributed databases, Data
warehousing and data mining.

Text book and Reference books:

1. “Database System Concepts” , 6th Edition by Abraham Silberschatz, Henry
F. Korth, S. Sudarshan,McGraw-Hill.
2. “Principles of Database and Knowledge – Base Systems”, Vol 1 by J. D.
Ullman, Computer Science Press.
3. Database Management Systems, R.P. Mahapatra, Khanna Publishing House,
New Delhi (AICTE Recommended Textbook – 2018)
4. “Fundamentals of Database Systems” , 5th Edition by R. Elmasri and S.Navathe,
5. PearsonEducation “Foundations of Databases”, Reprint by SergeAbiteboul, Richard Hull, Victor Vianu,Addison-
Wesley

18
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Human Computer Interaction

Code:OECAIML-601B
Contact: 3L

Name of the Course: Human Computer Interaction

Course Code: OECAIML- Semester: VI
601B
Duration: 6 months Maximum Marks:100
Teaching Scheme Examination Scheme

Theory:3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz: 10 marks
Attendance : 5 marks
Practical: NIL End Semester Exam :70 Marks
Credit Points: 3

Unit Content Hrs/U Marks/

nit Unit
9
1 Human: I/O channels – Memory – Reasoning and problem solving;
The computer: Devices – Memory – processing and networks;
Interaction: Models – frameworks – Ergonomics – styles – elements –
interactivity- Paradigms.
Interactive Design basics – process – scenarios – navigation – screen 11
2 design –
Iteration and prototyping. HCI in software process – software life cycle
–
usability engineering – Prototyping in practice – design rationale.
Design rules
– principles, standards, guidelines, rules. Evaluation Techniques –
Universal
Design.

Cognitive models –Socio-Organizational issues and stake holder

3. requirements 8
–Communication and collaboration models-Hypertext,
Multimedia and WWW.

4. Mobile Ecosystem: Platforms, Application frameworks- Types of 8

Mobile
Applications: Widgets, Applications, Games- Mobile Information
Architecture,
Mobile 2.0, Mobile Design: Elements of Mobile Design,
Tools.

19
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

5. Designing Web Interfaces – Drag & Drop, Direct Selection, Contextual 8

Tools,
Overlays, Inlays and Virtual Pages, Process Flow. Case
Studies.
6. Recent Trends: Speech Recognition and Translation, 3
Multimodal System

Text book and Reference books:

1. Theodor Richardson, Charles N Thies, Secure Software Design, Jones & Bartlett
2. Kenneth R. van Wyk, Mark G. Graff, Dan S. Peters, Diana L. Burley, Enterprise Software
Security,Addison Wesley.

Subject: Neural Networks

Course Code: OECAIML- Semester: VI

601C
Duration: 36 Maximum Marks: 100
Teaching Scheme Examination Scheme
Theory: 3 Hrs./week End Semester Exam: 70
Tutorial: 0 Attendance : 5
Practical: Continuous Assessment:25
Credit: 3

Aim:
Sl. No.
1. Develop algorithms simulating human brain.
2. Implement Neural Networks in Tensor Flow for solving problems.

3. Explore the essentials of Deep Learning and Deep Network architectures.

4. Define, train and use a Deep Neural Network for solving real world problems thatrequire
artificial Intelligence based solutions.
Objective:
Sl. No.
1. To acquire knowledge on the basics of neural networks.
2. To implement neural networks using computational tools for variety of problems.
3. To explore various deep learning algorithms.
Pre-Requisite:
Sl. No.
1. Calculus, Linear Algebra
2. Probability & Statistics
3. Ability to code in R/Python
Contents Hrs./week
Chapter Name of the Topic Hours Marks
01 Introduction 3 5
Various paradigms of earning problems, Perspectives and
Issues in deep learning framework, review of fundamentallearning
techniques.

20
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

02 6 10
Feed forward neural network

Artificial Neural Network, activation function, multi-layer

neural network,cardinality, operations, and properties of fuzzyrelations.
03 Training Neural Network 6 15
Risk minimization, loss function, backpropagation,
regularization, model selection, and optimization.
04 Conditional Random Fields 9 15
Linear chain, partition function, Markov network, Belief propagation,
Training CRFs, Hidden Markov Model, Entropy.
05 Deep Learning 6 15
Deep Feed Forward network, regularizations, training deep models,
dropouts, Convolutional Neural Network, RecurrentNeural Network,
Deep Belief Network.
06 Deep Learning research 6 10
Object recognition, sparse coding, computer vision, naturallanguage
Sub Total: 36 70
Internal Assessment Examination & Preparation of Semester 4 30
Examination
Total: 40 100
List of Books
Text Books:
Name of Author Title of the Book Edition/ISSN/ISBN Name of the Publisher
Rajiv Chopra Deep Learning First Edition Khanna Book
(AICTE Recommended Publishing
Textbook)
Goodfellow, Deep Learning MIT Press
I.,Bengio,Y.,and
Courville A.,
Satish Kumar Neural Networks: A Tata McGraw-Hill
Classroom Approach
Reference Books:
Bishop, C. ,M. Pattern Recognition Springer
and Machine Learning
Yegnanarayana, B. Artificial Neural PHI Learning Pvt. Ltd
Networks
Golub, G.,H., and Matrix Computations JHU Press
VanLoan,C.,F.

21
 Maulana Abul Kalam Azad University of Technology, West Bengal
(Formerly West Bengal University of Technology)
Syllabus for B. Tech in CSE (Artificial Intelligence and Machine Learning)
(Applicable from the academic session 2020-2021)

Name of the Course: Cryptography & Network Security

Course Code: Semester: VI
OEC-AIML 601D
Duration: 6 months Maximum Marks: 100
Teaching Scheme Examination Scheme

Theory: 3 hrs./week Mid Semester exam: 15

Tutorial: NIL Assignment and Quiz: 10 marks
Attendance: 5 marks
Practical: NIL End Semester Exam : 70 Marks
Credit Points: 3

Computer Security Concepts, The OSI Security Architecture, Security Attacks, Security
Services, Security Mechanisms , A Model for Network Security, Classical Encryption
Techniques, Symmetric Cipher Model, Substitution Techniques, Transposition Techniques,
Rotor Machines, Steganography, Cryptographic Tools, Confidentiality with Symmetric
Encryption, Message Authentication and Hash Functions, Public-Key Encryption, Digital
Signatures and Key Management, Random and Pseudorandom Numbers, Practical Application:
Encryption of Stored Data, User Authentication, Means of Authentication, Password-Based
Authentication, Token-Based Authentication, Biometric Authentication, Remote User
Authentication, Security Issues for User Authentication, Malicious Software, Types of Malicious
Software (Malware), Propagation—Infected Content—Viruses, Propagation—Vulnerability
Exploit—Worms, Propagation—Social Engineering—SPAM Email, Trojans, Payload—System
Corruption, Payload—Attack Agent—Zombie, Bots, Payload—Information Theft—Key loggers,
Phishing, Spyware, Payload—Stealthing— Backdoors, Rootkits, Countermeasures, Firewalls
and Intrusion Prevention Systems, the Need for Firewalls, Firewall Characteristic, Types of
Firewalls, Firewall Basing, Firewall Location and Configurations, Intrusion Prevention Systems.

Text Books:
1. Cryptography and Network Security: Principles and Practice by William Stalings 6th
Edition published by PHI (2011)
2. Computer security principles and practice, William Stallings, Lawrie Brown, third
edition, Prentice-Hall, 2011
3. Cryptography and Network Security, V.K. Jain, Khanna Publishing House

22