Scribd
Upload
52 views

Soft Computing Syllabus

This document outlines the instructions for a paper on soft computing. It divides the exam into 4 units covering topics like neural networks, fuzzy logic, fuzzy logic applications, and neuro-fuzzy systems. It specifies that the exam will have 1 compulsory question covering the entire syllabus worth 25 marks and 4 other unit-specific questions worth 12.5 marks each, but students only need to attempt 1 question per unit. The document provides an overview of the topics and number of hours covered in each unit, as well as textbooks and references for the course.

Uploaded by

piyanshu agrawal
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
52 views

Soft Computing Syllabus

This document outlines the instructions for a paper on soft computing. It divides the exam into 4 units covering topics like neural networks, fuzzy logic, fuzzy logic applications, and neuro-fuzzy systems. It specifies that the exam will have 1 compulsory question covering the entire syllabus worth 25 marks and 4 other unit-specific questions worth 12.5 marks each, but students only need to attempt 1 question per unit. The document provides an overview of the topics and number of hours covered in each unit, as well as textbooks and references for the course.

Uploaded by

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

Code No.

: ETCS 406 L T C
Paper: Soft Computing 3 1 4
INSTRUCTIONS TO PAPER SETTERS: MAXIMUM MARKS: 75
1. Question No. 1 should be compulsory and cover the entire syllabus. This question should have objective or short answer type questions. It should be of 25 marks.
2. Apart from question no. 1, rest of the paper shall consist of four units as per the syllabus. Every unit should have two questions. However, student may be asked to attempt only 1
question from each unit. Each question should be of 12.5 marks.
UNIT I
Neural Networks: History, overview of biological Neuro-system, Mathematical Models of Neurons, ANN architecture,
Learning rules, Learning Paradigms-Supervised, Unsupervised and reinforcement Learning, ANN training Algorithms-
perceptions, Training rules, Delta, Back Propagation Algorithm, Multilayer Perceptron Model, Hopfield Networks,
Associative Memories, Applications of Artificial Neural Networks. [No. of Hrs.: 11]
UNIT II
Fuzzy Logic: Introduction to Fuzzy Logic, Classical and Fuzzy Sets: Overview of Classical Sets, Membership Function,
Fuzzy rule generation.
Operations on Fuzzy Sets: Compliment, Intersections, Unions, Combinations of Operations, Aggregation Operations.
[No. of Hrs.: 11]
Fuzzy Arithmetic: Fuzzy Numbers, Linguistic Variables, Arithmetic Operations on Intervals & Numbers, Lattice of Fuzzy
Numbers, Fuzzy Equations.
UNIT III
Fuzzy Logic: Classical Logic, Multivalued Logics, Fuzzy Propositions, Fuzzy Qualifiers, Linguistic Hedges.
[No. of Hrs.: 11]
Uncertainty based Information: Information & Uncertainty, Nonspecificity of Fuzzy & Crisp Sets, Fuzziness of Fuzzy Sets.
UNIT IV
Introduction of Neuro-Fuzzy Systems, Architecture of Neuro Fuzzy Networks.
Application of Fuzzy Logic: Medicine, Economics etc.
Genetic Algorithm: An Overview, GA in problem solving, Implementation of GA
[No. of Hrs.: 11]
TEXT BOOKS:
1. J. A. Anderson, An Introduction to Neural Networks, PHI, 1999.
2. Hertz J. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley, California,
1991.
3. G.J. Klir & B. Yuan, Fuzzy Sets & Fuzzy Logic, PHI, 1995.
REFERENCE BOOKS:
1. Neural Networks-A Comprehensive Foundations, Prentice-Hall International, New Jersey, 1999.
2. J. A. Freeman, D.M. Skapura, Neural Networks: Algorithms, Applications and Programming Techniques,
Addison Wesley, Reading, Mass, (1992).
3. Melanie Mitchell, An Introduction to Genetic Algorithm, PHI, 1998.
BACHELOR OF TECHNOLOGY http://www.ipu.ac.in/syllabus/affiliated/sybtechcse.htm
73 of 78 05-Jun-14 5:10 PM

You might also like