Scribd
Upload
54 views

C

This document outlines the course objectives, expected outcomes, modules, and reference books for CSE5009 Soft Computing. The course aims to provide students with knowledge of neural networks, fuzzy logic, and genetic algorithms. It covers topics like artificial neural networks, supervised and unsupervised learning networks, fuzzy sets and relations, fuzzy logic systems, and genetic algorithms. The expected outcomes are for students to apply neural networks, fuzzy logic, and genetic algorithms to solve engineering problems.

Uploaded by

;(
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
54 views

C

This document outlines the course objectives, expected outcomes, modules, and reference books for CSE5009 Soft Computing. The course aims to provide students with knowledge of neural networks, fuzzy logic, and genetic algorithms. It covers topics like artificial neural networks, supervised and unsupervised learning networks, fuzzy sets and relations, fuzzy logic systems, and genetic algorithms. The expected outcomes are for students to apply neural networks, fuzzy logic, and genetic algorithms to solve engineering problems.

Uploaded by

;(
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

CSE5009 Soft Computing L T P J C

3 0 0 0 3
Version : 1.00
Pre-requisite: Nil
Course Objectives:
 To expose the students to the concepts of neural networks, fuzzy logic and genetic algorithms
 To provide comprehensive knowledge of fuzzy logic inference system and fuzzy logic control
 To provide adequate knowledge on applications of neural networks, fuzzy logic and genetic algorithms
in solving engineering problems.
Expected Outcomes:
The student will be able
 To know how to use neural networks for solving different problems related to pattern recognition,
function approximation and data visualization.
 To apply the rules of fuzzy logic for solving engineering problems.
Student Learning Outcomes (SLO): 1,2,9,17
Module:1 Artificial Neural Networks 5 hours SLO:
1,2
Soft computing vs. hard computing, types and applications of soft computing techniques. Artificial neural
networks and their biological motivation – Terminology – Models of neuron –Topology – characteristics
of artificial neural networks – types of activation functions-, learning methods – error correction learning
– Hebbian learning, Linear separability and XOR problem

Module:2 Supervised Learning Networks 6 hours SLO:


1,2
Discrete and continuous Perceptron, adaline, multilayer Perceptron, Back Propagation algorithm,
limitations and improvements

Module:3 Associative Memory Networks 6 hours SLO:1,2,


Autoassociation, heteroassociation, recall and cross talk- Linear auto associator – Bi-directional
associative memory – Hopfield neural network

Module:4 Unsupervised Learning Networks 6 hours SLO:


1,2
Neural Nets based on competition-Max net – Mexican Hat – Hamming net - Kohonen Self organizing
Feature Map – Counter propagation – Learning Vector Quantization Adaptive Resonance Theory

Module:5 Fuzzy Sets and Fuzzy Relations 5 hours SLO:


1,2
Introduction –classical sets and fuzzy sets –classical relations and fuzzy relations –membership functions
–fuzzy to crisp conversion, Fuzzy numbers, vectors, and extension principle

Module:6 Fuzzy Logic System 6 hours SLO:1,2


Fuzzy Logic, Fuzzy knowledge and rule based system, fuzzy decision making –fuzzy logic modeling and
control.

Module:7 Genetic Algorithm 8 hours SLO: 1,2


Basic concepts, encoding, fitness function, reproduction, Genetic modeling: Inheritance operator, cross
over, inversion & deletion, mutation operator, Bitwise operator, Generational Cycle, Convergence of GA,
Applications & advances in GA, Differences & similarities between GA & other traditional method

Module:8 Contemporary Issues 3 hours SLO:1,2,9,17

Total Lecture: 45 hours


Reference Books:
1. S, Rajasekaran & G.A. Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic & Genetic Algorithms,
Synthesis & applications”, PHI Publication.
2. Lauren Fausett, “Fundamentals of Neural Networks-Architectures, algorithms and applications”,
Pearson Education Inc., 2004.
3. Timothy J. Ross, “Fuzzy Logic with Engineering Applications”, John Wiley and Sons, 2004.
4. S.N. Sivanandam & S.N. Deepa, “Principles of Soft Computing”, Wiley Publications Rich E and
Knight K, Artificial Intelligence, TMH, New Delhi.
5. S. Haykin, “Neural Networks, A Comprehensive Foundation“, Pearson Education Inc., 2004.
6 Jacek. M. Zurada, “Introduction to Artificial Neural Systems”, Jaico Publishing House, 2001.

Date of Approval by the Academic Council 18.03.16

You might also like