Scribd
Upload
9 views4 pages

Soft Computing Index

The document outlines a comprehensive curriculum on Soft Computing, covering topics such as definitions, goals, and applications of soft computing, as well as artificial neural networks (ANN), fuzzy set theory, optimization techniques, and genetic algorithms. Each module includes detailed subtopics, including various learning types, neural network architectures, fuzzy logic principles, and optimization methods. Additionally, it provides insights into hybrid systems and their applications in the context of genetic algorithms.

Uploaded by

jebaasind2005
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
9 views4 pages

Soft Computing Index

The document outlines a comprehensive curriculum on Soft Computing, covering topics such as definitions, goals, and applications of soft computing, as well as artificial neural networks (ANN), fuzzy set theory, optimization techniques, and genetic algorithms. Each module includes detailed subtopics, including various learning types, neural network architectures, fuzzy logic principles, and optimization methods. Additionally, it provides insights into hybrid systems and their applications in the context of genetic algorithms.

Uploaded by

jebaasind2005
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/ 4

Module 1: INTRO TO SC

(Page no. are given so don’t include first Header page )


 Definitions - Computing, Hard Computing, Soft Computing - 2
 Difference between Hard and Soft Computing -2
 Goals of Soft Computing -2
 Constituents of Soft Computing -3
 Characteristics of Neuro-Computing and Soft Computing - 3
 Applications of Soft Computing - 4
 Learning and its Types – 4
 Supervised,
 Unsupervised, and
 Reinforcement.
Module 2: ANN – 6
 Intro to ANN - 7
 Neuron (Biological Concept) - 7
 Comparison of Biological vs. Artificial Neuron - 8
 Characteristics of ANN - 9
 Structure of ANN - Weights, Bias, Threshold, Learning Rate, Activation Function. - 9
 Activation Functions – Discrete, Continuous. - 10
 Discrete Activation Functions – 10
 Identity function.
 Binary Step function.
 Bipolar Step function.
 Continuous Activation Functions – 11
 Binary Sigmoidal function.
 Bipolar Sigmoidal function.
 RAMP function.
 Neural Network Architectures – 12
 Single Layer Feedforward network.
 Multi-Layer Feedforward network.
 Recurrent network.
 McCulloh-Pitts Neuron Model. - 14
 Hebbian Learning Rule. - 15
 Winner Takes All. - 15
 Back Propagation Network (BPN) - 16
 Perceptron Network. - 19
 Linear Separability. - 19
 Self-Organizing Maps (SOMs). - 20
 Kohonen Network (KSOMs). - 21
 Linear Vector Quantization (LVQs). - 22
Module 3: FUZZY SET THEORY
 Fuzzy Logic and the Need for Fuzzy Logic. - 43
 Classical and Fuzzy Sets. - 43
 Properties of Crisp Sets.
 Operations on Crisp Sets.
 Degree of Membership.
 Properties of Fuzzy Sets.
 Operations on Fuzzy Sets.
 Classical and Fuzzy Relations - 46
 Crisp Cartesian Product.
 Crisp Relations.
 Properties of Crisp Relations.
 Operations on Crisp Relations.
 Composition on Crisp Relations (w/ Example).
 Fuzzy Cartesian Product.
 Fuzzy Relations.
 Properties of Fuzzy Relations.
 Operations on Fuzzy Relations.
 Composition on Fuzzy Relations (w/ Example).
 Tolerance and Equivalence Relations - 50
 Crisp Tolerance and Equivalence.
 Fuzzy Tolerance and Equivalence.
 Membership Functions. - 51
 Methods for assigning membership values.
 Features of membership functions.
 Fuzzification. - 53
 De-Fuzzification. - 54
 Lambda 𝝀-cut (alpha-cut). - 58
 Fuzzy Extension Principle. - 59
Refer hand-written notes for Types of Membership functions & Fuzzy Controller
(MAMDANI) sums. (index given below at bottom )
Module 4: FUZZY SET THEORY - 60
 Introduction to Hybrid Systems. - 61
 Neuro-Fuzzy Hybrid Systems. - 62
 Co-Operative NFS.
 General NFS.
 Fuzzy Inference System. - 63
 ANFIS. - 65
 Hybrid Learning Rule. - 67
Module 5: INTRODUCTION TO OPTIMIZATION TECHNIQUES - 68
 Introduction to Optimization. - 69
 Derivative Based Optimization. - 69
 Steepest (Gradient) Descent.
 Newton Method.
 Derivative Free Optimization. - 72
 Simulated Annealing.
 Random Search.
 Downhill Simplex Search.

Module 6: GENETIC ALGORITHMS AND ITS APPLICATIONS - 77


 Introduction to GA. - 78
 Simple GA (Algorithm). – 79
 Inheritance Operators. - 80
 Bitwise Operators. - 81
 Encoding. - 83
 Selection Techniques. - 85
Roulette Wheel, Random, Rank, Tournament, Elitism.
 Crossover Techniques. - 86
Single Point, Two Point, Multi Point, Uniform, Three Parent, Reduced Surrogate,
Shuffle, Ordered, Partially Matched (PMX), Precedence Preservative (PPX).
 Mutation Techniques. - 89
Flipping, Interchanging, Reversing.
 Replacement Techniques. - 90
Random, Weak Parent, Both Parents.
 Convergence of GA. – 90
 Advantages and Disadvantages. - 91
 Applications of GA. - 91
Extra Notes Index

 MP neuron – 3
 Learning Method – 7
 Unsupervised Learning – 9
 Reinforced Learning – 10
 Linear Seprablility – 11
 Kohonen’s Self Organizing Network – 14
 Linear Vector Quantization – 17
 Fuzzy Set Theory – 20
 Optimization Technique – 26
 Newton’s Method – 28
 Mamdani Model Sum - 30

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy