Scribd
Upload
57 views2 pages

Syllabus Soft Computing - 19-20

This document provides an overview of the topics covered in 4 units of an introduction to soft computing course. Unit 1 introduces soft computing techniques including neural networks, fuzzy systems, and evolutionary algorithms. It also covers expert systems design and neural network learning algorithms. Unit 2 focuses on fuzzy logic, including fuzzy set theory, operations, and fuzzy inference systems. Unit 3 discusses genetic algorithms and other evolutionary algorithms like particle swarm optimization. Unit 4 introduces deep neural networks, convolutional neural networks, and hybrid soft computing systems combining techniques like neuro-fuzzy systems. Textbooks and references for further reading are also provided.

Uploaded by

Vinay Rai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
57 views2 pages

Syllabus Soft Computing - 19-20

This document provides an overview of the topics covered in 4 units of an introduction to soft computing course. Unit 1 introduces soft computing techniques including neural networks, fuzzy systems, and evolutionary algorithms. It also covers expert systems design and neural network learning algorithms. Unit 2 focuses on fuzzy logic, including fuzzy set theory, operations, and fuzzy inference systems. Unit 3 discusses genetic algorithms and other evolutionary algorithms like particle swarm optimization. Unit 4 introduces deep neural networks, convolutional neural networks, and hybrid soft computing systems combining techniques like neuro-fuzzy systems. Textbooks and references for further reading are also provided.

Uploaded by

Vinay Rai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

UNIT 1

Introduction to Soft Computing: Soft Computing versus Hard Computing, Soft-Computing


Techniques: Artificial Neural Networks, Fuzzy Systems, Evolutionary Algorithm.

Expert Systems: Expert System Design. Types of Problems: Classification, Functional


Approximations, Optimizations.

Neural Networks: Mc-Culloch Pitt’s neuron model, Activation functions, Basic gates, Neural
learning. Training algorithms- Hebbian learning rule, perceptron learning rule, Delta learning
rule, Widrow-Hoff learning rule related problems. Error back propagation algorithm or
generalized delta rule. Setting of parameter values and design considerations (Initialization
of weights, Frequency of weight updates, Choice of learning rate, Momentum,
Generalizability, Network size, Sample size, Non-numeric inputs).

UNIT -2

Fuzzy Logic: Introduction, Classical Set Theory (Crisp Set): Operations & Properties, Fuzzy Set
Theory: Operations & Properties, Membership Functions and types, Fuzzy v/s Crisp Sets,
Classical relations (Cartesian product) and Fuzzy relations: Cardinality, Operations,
Properties and Composition, Tolerance and Equivalence Relations.

Crisp Logic vs Fuzzy logic, Fuzzy logic operations: AND, OR, NOT, Implication,Aggregation
and Deffuzification, Lambda-cuts or Alpha-cuts for fuzzy, Types of defuzzification. Fuzzy
Inference Systems and its design, Fuzzy Process, Type-2 fuzzy sets, Sugeno Fuzzy System.

UNIT -3

Genetic Algorithms: Concept, Solution, Initial Population, Genetic Operators, Fitness


Function, Stopping Condition. Fitness Scaling, Selection, Mutation, Crossover, Other Genetic
Operators, Algorithm Working, Diversity.

Other Evolutionary Algorithms: Particle Swarm Optimization, Ant Colony Optimizations,


Traveling Salesman Problem.

UNIT -4

Deep Neural Networks: Introduction & Necessity of deep neural networks (DNN),Example:
Auto encoder DNN, Convolutional neural networks: Convolution operation,Motivation and
Pooling.

Hybrid Systems: Sequential, Auxiliary and Embedded Hybrid Systems, Neuro-FuzzyHybrid


System: Comparison, Characteristics & Classification, Neuro-Genetic Hybrid:Properties, GA
based Back Propagation Network and its advantages, Genetic- Fuzzy andFuzzy-Genetic
Hybrid systems: Tuning, Learning, Advantages.
TEXTBOOKS

1. Rajasekaran, G. A. Vijayalakshmi Pai; Neural Networks, Fuzzy Logic and


GenericAlgorithm, PHI Learning Pvt. Ltd.
2. Anupam Shukla, Ritu Tiwari, Rahul Kala; Real Life Applications of Soft Computing;
CRC Press
3. S. N. Sivanandan and S. N. Deepa, Principles of Soft Computing, 2 nd Edition,
WileyIndia.
4. Kishan Mehrotra, Chilukuri Mohan, Sanjay Ranka; Elements of Artificial Neural
Network;Penram Publications.
REFERENCES

1. J. Zurada; Introduction to Artificial neural network; Jaico Publications.


2. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press.
3. Charu C. Aggarwal, Neural Networks and Deep learning, Springer Publications.
4. Timothy J. Ross; Fuzzy Logic with Engineering Applications, 3 rd Ed.; Wiley-India

You might also like