Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
128 views

EC360 Soft Computing - Syllabus PDF

This document outlines the course objectives, syllabus, expected outcomes, and course plan for a Soft Computing course offered in 2016. The course introduces concepts of fuzzy logic, neural networks, and genetic algorithms. It covers topics like fuzzy sets and relations, neural network architectures, backpropagation, and genetic algorithms. Students are expected to learn how to apply soft computing techniques to problems involving pattern classification, optimization, and more. The course is assessed through internal exams, assignments, and an end semester exam involving both theoretical and practical questions.

Uploaded by

voxov
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
128 views

EC360 Soft Computing - Syllabus PDF

This document outlines the course objectives, syllabus, expected outcomes, and course plan for a Soft Computing course offered in 2016. The course introduces concepts of fuzzy logic, neural networks, and genetic algorithms. It covers topics like fuzzy sets and relations, neural network architectures, backpropagation, and genetic algorithms. Students are expected to learn how to apply soft computing techniques to problems involving pattern classification, optimization, and more. The course is assessed through internal exams, assignments, and an end semester exam involving both theoretical and practical questions.

Uploaded by

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

COURSE YEAR OF

CODE COURSE NAME L-T-P-C INTRODUCTION


EC360 Soft Computing 3-0-0 -3 2016
Prerequisite: NIL
Course objectives:
1. To familiarize various components of soft computing like fuzzy logic, neural networks
and genetic algorithm.
2. To give an overview of fuzzy Logic and to understand the concepts and terminologies of
fuzzy systems
3. To give a description on artificial neural networks with its advantages and application.
4. To study the fundamentals of Genetic Algorithm (GA).
5. To understand the concepts of hybrid systems.
Syllabus:
Fuzzy sets and systems. Neural Networks - Applications - typical architecture, pattern
Classification and pattern Association. Fundamentals of Genetic Algorithm, AI search
algorithm and hybrid structure.
Expected outcome:
The students will be able to:
1. Identify and describe soft computing techniques and their roles in building intelligent
Machines.
2. Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems
3. Recognize the feasibility of applying a soft computing methodology for a particular
Problem.
4. Apply neural networks to pattern classification and regression problems.
5. Apply genetic algorithms to combinatorial optimization problems
Text Books:
1. D.E. Goldberg, "Genetic Algorithms: Search, Optimization and Machine Learning",
Addison Wesley,N.Y, 1989.
2. Laurene V. Fausett, (1993) “Fundamentals of Neural Networks: Architecture,
Algorithms and Applications", Prentice Hall.
3. Timothy J. Ross, “Fuzzy Logic with Engineering Applications” Wiley India.
References:
1. Ibrahim A. M., Introduction to Applied Fuzzy Electronics, PHI, 2013.
2. J. Yen and R. Langari, Fuzzy Logic, Intelligence, Control and Information, Pearson
Education.
3. K.H.Lee, First Course on Fuzzy Theory and Applications, Springer-Verlag.
4. Lin C. T. and C.S. G. Lee, Neural Fuzzy Systems, Prentice Hall, 1996.
5. S. Rajsekaran & G.A. Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic and Genetic
Algorithm: Synthesis and Applications” Prentice Hall of India.
6. S.N. Sivanandan and S.N. Deepa, Principles of Soft Computing, Wiley India, 2007.
ISBN: 10: 81-265-1075-7.
Course Plan
Module Course content End
Sem.
Hours
Exam
Marks
Soft computing: Introduction, soft computing vs hard
computing, Fuzzy Computing, Neural Computing, Genetic 2
Algorithms. applications of soft computing
Introduction to fuzzy sets and systems-crispness, vagueness, 15
I
uncertainty and fuzziness. Basics of fuzzy sets, membership
3
functions, support of a fuzzy set height, normalized fuzzy set,
alpha cuts.
Type- 2 fuzzy sets. Operation on fuzzy set-complement,
4
intersection, union, Demorgan's Law Equality & subset hood.
II Extension Principle and its application, Fuzzy relation- 15
operations, projection, max-min, min-max composition, 3
cylindrical extension.
FIRST INTERNAL EXAM
Reflexivity, symmetry and transitivity of fuzzy relations. Fuzzy
4
prepositions, fuzzy connectives, linguistic variables, hedges.
III Approximate reasoning or fuzzy inference, Fuzzy rule based 15
system. Fuzzification and defuzzification using centroid, centre 4
of sums.
Introduction to Neural Networks - Applications –Biological
neuron- Typical architecture of Artificial Neural Networks - 4
IV Common activation function. 15
McCulloh Pitts Neuron – Architecture, logic implementatons.
4
Supervised and Unsupervised learning
SECOND INTERNAL EXAM
Linear Separability, Pattern Classification: Perceptrons 2
V Back propagation network and its architecture, Back 20
4
propagation learning, back propagation algorithm
Genetic Algorithm Basic concepts, Initialization and selection,
5
VI Survival of the Fittest - Fitness Computations. 20
Operators - Cross over, Mutation. 3
END SEMESTER EXAM
Question Paper ( End semester exam)
Max. Marks: 100 Time : 3 hours

The question paper shall consist of three parts. Part A covers modules I and II, Part B covers
modules III and IV, and Part C covers modules V and VI. Each part has three questions
uniformly covering the two modules and each question can have maximum four subdivisions.
In each part, any two questions are to be answered. Mark patterns are as per the syllabus
with 50 % for theory, derivation, proof and 50% for logical/numerical problems.

You might also like