School of Computer Engineering

Kalinga Institute of Industrial Technology (KIIT)

Deemed to be University
Bhubaneswar-751024

Semester: 5th
Session: Autumn 2024

Course Plan

Course Code : CS 30011

Course Title : Computational Intelligence
LTP Structure : L T P Total Credit
3 0 0 3 3

Instructor:
Name : Dr. Sujoy Datta
Chamber : F-102, Block-C, Campus-14
Email : [email protected]
Contact Number : 8093713885

Course Objective
This is an elective course, open to 3rd year B.Tech (CS, CSCE, and IT) students. Computational Intelligence (Soft
Computing) is a new concept for advanced information processing. The objective of Computational Intelligence
approaches is to introduce a new approach for analyzing and creating flexible information processing of humans
such as sensing, understanding, learning, recognizing, and thinking. Our aim is to realize three main methodologies
of Computational Intelligence and their hybridization in the first few classes. Following this, we discuss in details
the three methodologies which are biologically and linguistically motivated computational paradigms such as
Neural Networks, Fuzzy Systems, Evolutionary Computation and Hybrid Neuro-Fuzzy Models. Finally, students
will be acquainted with designing intelligent systems and provide them with a working knowledge for building
these systems.

Course Outcomes
Identify the basic concepts and characteristics of soft computing and its associated
CO1:
methodologies.
Assess concepts of artificial neural networks and apply neural networks to various
CO2:
classification problems.
CO3: Apply various set theoretic operations in fuzzy sets.
Analyze fuzzy rules, fuzzy reasoning and various fuzzy and neuro-fuzzy inference
CO4:
systems.
Understand derivative free optimization and apply genetic algorithms to optimization
CO5:
problems.
CO6: Apply and evaluate swarm-based optimization techniques in real-world problem solving.
Course Contents
Topics No. of lectures Course
Outcome
Introduction to Soft Computing and Neuro- 3 CO1
Fuzzy System (1-3)
Introduction to Concept of computing
"Soft" computing versus "Hard" computing
Conventional AI
Constituents of Soft Computing
Neuro-Fuzzy Systems
Artificial Neural Networks (ANN) 15 CO2
Introduction to ANN (4 -18)
Adaline and Madaline
Learning algorithms
Perceptron
Multilayer Perceptron (MLP) and Backpropagation (BP)
algorithm
Radial Basis Function Networks (RBF)
Fuzzy Set Theory 6 CO3
Fuzzy sets, Basic Definition and Terminology (19 - 24)
Member Function Formulation and Parameterization
Set-theoretic Operations and Fuzzy sets operations
(Union, Intersection and Complement)
Fuzzy Rules, Fuzzy Reasoning and Fuzzy 7 CO4
Inference Systems (25 - 31)
Extension Principle and Fuzzy Relations
Fuzzy If-Then Rules and Fuzzy Reasoning
Fuzzy Inference Systems: Mamdani Fuzzy Models,
Sugeno Fuzzy Models, Tsukamoto Fuzzy Models
Adaptive Neuro Fuzzy Inference Systems (ANFIS)
Optimization 3 CO5
Derivative-based Optimization and Derivative-free (32 - 34)
Optimization
Genetic Algorithms (GA)
Differential Evolution (DE)
Swarm Intelligence 5 CO6
Particle Swarm Optimization (35 - 39)
Ant Colony Optimization
Artificial Bee Colony Optimization

Day-wise Lesson Plan

Week Lecture Topics

No.
Week - 1 1 Introduction to Soft Computing, Techniques, Applications, Advantages,
Disadvantages
2 Constituents of Soft Computing
3 Neuro-Fuzzy Systems
Week - 2 4 Introduction to Artificial Neural Networks, Biological Model Vs
Mathematical Model
5 ANN architecture, ANN Building Blocks
6 Adaline and Madaline
Activity - 1
Week – 3 7 Supervised vs Unsupervised Learning, Gradient descent method
8 McCulloch Pitts Model, Modelling logic gates, limitations
9 Linear separability, Single Layer Perceptron, Learning Rule & Model
Week - 4 10 Multilayer Perceptron and its applications in real world
11 Back propagation Algorithm - 1
12 Back propagation Algorithm - 2
 Activity - 2
Week - 5 13 Factors affecting back propagation training, Advantages and
Disadvantages
14 Introduction to Radial Basis Function Networks (RBFN)
15 RBFN Learning Algorithms
Week - 6 16 XOR – Problem Solving using RBFN
17 Problem solving on real world applications
18 Basics of third-generation neural networks
Activity - 3
Mid-Semester Examination
Week - 7 19 Crisp and Fuzzy sets
20 Basic Definition and Terminology
21 Member Functions Formulation and Parameterization - 1
Week - 8 22 Member Functions Formulation and Parameterization - 2
23 Set-theoretic operations and Fussy sets operations
24 Fuzzy sets operations, T-norm and T-conorm
Activity - 4
Week - 9 25 Extension Principle and Fuzzy Relations
26 Fuzzy systems-quantifiers, fuzzy inference
27 Fuzzy If-Then Rules
Week - 10 28 Fuzzy Reasoning
29 Fuzzy Inference Systems: Mamdani Fuzzy Models
30 Sugeno Fuzzy Models, Tsukamoto Fuzzy Models
Activity - 5
Week - 11 31 Adaptive Neuro Fuzzy Inference Systems (ANFIS) architecture
32 Derivative-based Optimization and Derivative-free Optimization
33 Concept of Genetic Algorithms (GA), GA Operators
Week - 12 34 Differential Evolution (DE) as modified GA, Problem solving
35 Swarm Intelligence concept, examples, applications
36 Particle Swarm Optimization (PSO) model, velocity and position update
equations, problem solving
Week - 13 37 PSO variants, Binary PSO
38 Ant Colony Optimization concepts and applications
39 Artificial Bee Colony Optimization concepts and applications
Activity - 6
End-Semester Examination

Text books:
1. Neuro-Fuzzy and Soft Computing, Jang, Sun, Mizutani, PHI/Pearson Education

Reference books:
1. Neural Network Design, M. T. Hagan, H. B. Demuth, Mark Beale, Thomson Learning, Vikash
Publishing House
2. Genetic Algorithms: Search, Optimization and Machine Learning, Davis E. Goldberg, Addison
Wesley, N.Y., 1989
3. Swarm Intelligence Algorithms: A Tutorial, Adam Slowik, Ed: CRC Press, 2020
4. Introduction to Soft Computing, Roy and Chakraborty, Pearson Education
5. Fuzzy Logic with Engineering Applications, Timothy J. Ross, McGraw-Hill, 1997
6. Neural Networks: A Comprehensive Foundation, Simon Haykin, Prentice Hall
7. Neural Networks, Fuzzy Logic and Genetic Algorithms, S. Rajasekaran and G.A.V. Pai, PHI, 2003

Assessment plan for activity-based teaching

Considering the guidelines circulated and after discussing with the faculty members, following activity-based
teaching and learning is proposed to have the uniformity of subject delivery in all sections.

Sr # Assessment Component Time Weightage/ Schedule

Marks
 1 Mid-Semester Examination 1.5 Hours 20 Refer Details in Student
Handbook
2 Activity based Teaching and Learning: Based on 30 Throughout semester
Quiz, Assignment, Class Test, Viva, activities
and/or Mini-project
3 End-Semester Examination 2.5 Hours 50 Refer Details in Student
Handbook

There will be a minimum of 5 short activities (quizzes/assignments/class test/viva/mini project)

over the semester, at the end of every unit.