Scribd
Upload
234 views

Elective-II Soft Computing

This document outlines the course objectives, outcomes, modules, and practicals for a 5-credit Soft Computing course. The course aims to conceptualize neural networks and introduce concepts like fuzzy sets, fuzzy logic, and genetic algorithms. The 14 modules cover topics ranging from neural networks and fuzzy set theory to hybrid systems and genetic algorithms. Students are evaluated based on laboratory work, assignments, attendance, and an oral exam assessing their ability to apply concepts from the course. Practicals involve case studies and implementing algorithms for fuzzy sets, neural networks, genetic algorithms, and more.

Uploaded by

Catlin Kara
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
234 views

Elective-II Soft Computing

This document outlines the course objectives, outcomes, modules, and practicals for a 5-credit Soft Computing course. The course aims to conceptualize neural networks and introduce concepts like fuzzy sets, fuzzy logic, and genetic algorithms. The 14 modules cover topics ranging from neural networks and fuzzy set theory to hybrid systems and genetic algorithms. Students are evaluated based on laboratory work, assignments, attendance, and an oral exam assessing their ability to apply concepts from the course. Practicals involve case studies and implementing algorithms for fuzzy sets, neural networks, genetic algorithms, and more.

Uploaded by

Catlin Kara
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Course Code Course/Subject Name Credits

CPE7025 Soft Computing 5

Objectives:
1. To Conceptualize the working of human brain using ANN.
2. To become familiar with neural networks that can learn from available examples and
generalize to form appropriate rules for inference systems.
3. To introduce the ideas of fuzzy sets, fuzzy logic and use of heuristics based on human
experience.
4. To provide the mathematical background for carrying out the optimization and
familiarizing genetic algorithm for seeking global optimum in self-learning situation.

Outcomes: Learner will be able to…


1. Ability to analyze and appreciate the applications which can use fuzzy logic.
2. Ability to design inference systems.
3. Ability to understand the difference between learning and programming and explore
practical applications of Neural Networks (NN).
4. Ability to appreciate the importance of optimizations and its use in computer engineering
fields and other domains.
5. Students would understand the efficiency of a hybrid system and how Neural Network
and fuzzy logic can be hybridized to form a Neuro-fuzzy network and its various
applications.

Module Detailed Contents Hours


01 Introduction to Soft Computing 04
1.1 Soft computing Constituents, Characteristics of Neuro
Computing and Soft Computing, Difference between Hard
Computing and Soft Computing, Concepts of Learning and
Adaptation.

02 Neural Networks 14
2.1 Basics of Neural Networks:
Introduction to Neural Networks, Biological Neural
Networks, McCulloch Pitt model,
2.2 Supervised Learning algorithms:
Perceptron (Single Layer, Multi layer), Linear separability,
Delta learning rule, Back Propagation algorithm,
2.3 Un-Supervised Learning algorithms: Hebbian Learning,
Winner take all, Self Organizing Maps, Learning Vector
Quantization.
03 Fuzzy Set Theory 14
3.1 Classical Sets and Fuzzy Sets, Classical Relations and Fuzzy
Relations, Properties of membership function, Fuzzy
extension principle, Fuzzy Systems- fuzzification,
defuzzification and fuzzy controllers.

04 Hybrid system 04
4.1 Introduction to Hybrid Systems, Adaptive Neuro Fuzzy
Inference System(ANFIS).
05 Introduction to Optimization Techniques 06
5.1 Derivative based optimization- Steepest Descent, Newton
method.
5.2 Derivative free optimization- Introduction to Evolutionary
Concepts.
06 Genetic Algorithms and its applications: 06
6.1 Inheritance Operators, Cross over types, inversion and
Deletion, Mutation Operator, Bit-wise Operators,
Convergence of GA, Applications of GA.

Term Work:
The distribution of marks for term work shall be as follows:
• Laboratory work (experiments/case studies): ………….. (15) Marks.
• Assignments:…….…………………………………… (05) Marks.
• Attendance ………………………………………. (05) Marks
TOTAL: ……………………………………………………. (25) Marks.

Practical/Oral examination:
Oral examination will be based on the above syllabus.

PRACTICALS:

All the programs should be implemented in C/C++/Java/MATLAB under Windows or Linux


environment. Experiments can also be conducted using available open source tools like
OCTAVE and SCILAB

LIST OF SC PRACTICAL / EXPERIMENTS

1. One case study on Fuzzy/Neural/GA based papers published in IEEE/ACM/Springer or any


prominent journal.

2. To implement Fuzzy Sets.


3. To implement Fuzzy Relations.

4. To implement Fuzzy Controllers.

5. To implement Basic Neural Network learning rules.

6. To implement any Supervised Learning algorithm.

7. To implement any Unsupervised Learning algorithm.

8. To implement a simple application using Genetic Algorithm.

Any other practical covering the syllabus topics and subtopics can be conducted.

Reference Books (for practicals) :


1. S.N.Sivanandam, S.N.Deepa "Principles of Soft Computing" Second Edition, Wiley
Publication.
2. S.Rajasekaran and G.A.Vijayalakshmi Pai "Neural Networks, Fuzzy Logic and Genetic
Algorithms" PHI Learning.
3. Hagan, Demuth, Beale,"Neural Network Design" CENGAGE Learning, India Edition.

4. Satish Kumar, “Neural Networks –A classroom approach”, Second Edition,TMH


Publication.

Text Books:
1. Timothy J.Ross "Fuzzy Logic With Engineering Applications" Wiley.
2. S.N.Sivanandam, S.N.Deepa "Principles of Soft Computing" Second Edition, Wiley
Publication.
3. S.Rajasekaran and G.A.Vijayalakshmi Pai "Neural Networks, Fuzzy Logic and Genetic
Algorithms" PHI Learning.
4. J.-S.R.Jang "Neuro-Fuzzy and Soft Computing" PHI 2003.
5. Jacek.M.Zurada "Introduction to Artificial Neural Sytems" Jaico Publishing House.

Reference Books:
1. Satish Kumar "Neural Networks A Classroom Approach" Tata McGrawHill.
2. Zimmermann H.S "Fuzzy Set Theory and its Applications" Kluwer Academic Publishers.
3. Davis E.Goldberg, "Genetic Algorithms: Search, Optimization and Machine Learning",
Addison Wesley, N.Y., 1989.
4. Hagan, Demuth, Beale, "Neural Network Design" CENGAGE Learning, India Edition.

You might also like