Neural networks, fuzzy logic. and genetic algorithms: systhesis and applications (Record no. 3342)

MARC details
000 -LEADER
fixed length control field 10645nam a22001817a 4500
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9788120321861
040 ## - CATALOGING SOURCE
Transcribing agency CUS
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 006.32
Item number RAJ/N
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Rajasekaran, S.
245 ## - TITLE STATEMENT
Title Neural networks, fuzzy logic. and genetic algorithms: systhesis and applications
Statement of responsibility, etc. S. Rajasekaran and G. A. Vijayalakshmi Pai
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication, distribution, etc. Delhi:
Name of publisher, distributor, etc. PHI Learning Private Limited,
Date of publication, distribution, etc. 2014.
300 ## - PHYSICAL DESCRIPTION
Extent xvi, 439 p.
505 ## - FORMATTED CONTENTS NOTE
Formatted contents note 1 INTRODUCTION TO ARTIFICIAL INTELLIGENCE SYSTEMS<br/>1.1 Neural Networks 2<br/>1.2 Fuzzy Logic 3<br/>1.3 Genetic Algorithms 4<br/>1.4 Structiire of This book 5<br/>Summary 6<br/>References 6<br/>Part 1 NEURAL NETWORKS<br/>2 FUNDAMENTALS OF NEURAL NETWORKS<br/>2.1 Basic Concepts of Neural Networks II<br/>2.2 Human Brain 12<br/>2.3 Model of an Artificial Neuron 13<br/>2.4 Neural Network Architectures 16<br/>2.4.1 Single Layer Feedforward Network 17<br/>2.4.2 Multilayer Feedforward Network 18<br/>2.4.3 Recurrent Networks 18<br/>2.5 Characteristics of Neural Networks 19<br/>2.6 Learning Methods 19<br/>2.7 Taxonomy of Neural Network Architectures 21<br/>2.8 History of Neural Network Research 22<br/>2.9 Early Neural Network Architectures 23<br/>2.9.1 Rosenblatt's Perceptron 23<br/>2.9.2 ADALINE Network 28<br/>2.9.3 MADALINE Network 28<br/>2.10 Some Application Domains 30<br/>Summary 31<br/>Programming Assignment 31<br/>Suggested Further Reading 32<br/>References 32<br/>3 BACKFROPAGATION NETWORKS<br/>3.1 Architecture of a Backpropagation Network 35<br/>3.1.1 The Perceptron Model 35<br/>3.1.2 The Solution 36<br/>3.1.3 Single Layer Artificial Neural Network 39<br/>3.1.4 Model for Multilayer Perceptron 41<br/>3.2 Backpropagation Learning 42<br/>3.2.1 Input Layer Computation 43<br/>3.2.2 Hidden Layer Computation 43<br/>3.2.3 Output Layer Computation 44<br/>3.2.4 Calculation of Error 45<br/>3.2.5 Training of Neural Network 45<br/>3.2.6 Method of Steepest Descent 47<br/>3.2.7 Effect of Learning Rate *7]' 51<br/>3.2.8 Adding a Momentum Term 52<br/>3.2.9 Backpropagation Algorithm 53<br/>3.3 Illustration 56<br/>3.4 Applications 59<br/>3.4.1 Design of Journal Bearing 59<br/>3.4.2 Classification of Soil 64<br/>3.4.3 Hot Extrusion of Steel 65 .<br/>3.5 Effect of Tuning Parameters of the Backpropagation Neural Network<br/>3.6 Selection of Various Parameters in BPN 72<br/>3.6.1 Number of Hidden Nodes 72<br/>3.6.2 Momentum Coefficient a 73<br/>3.6.3 Sigmoidal Gain A 74<br/>3.6.4 Local Minima 74<br/>3.6.5 Learning Coefficient T] 74<br/>3.7 Variations of Standard Backpropagation Algorithm 75<br/>3.7.1 Decremental Iteration Procedure 75<br/>3.7.2 Adaptive Backpropagation (Accelerated Learning) 7o<br/>3.7.3 Genetic Algorithm Based Backpropagation 77<br/>3.7.4 Quick Prop Training 77<br/>3.7.5 Augmented BP Networks 77 , xt i<br/>3.7.6 Sequential Learning Approach for Single Hidden Layer Neura<br/>Networks 80<br/>3.8 Research Directions 80<br/>3.8.1 New Topologies 80<br/>3.8.2 Better Learning Algorithms 81<br/>3.8.3 Better Training Strategies 81<br/>3.8.4 Hardware Implementation 81<br/>3.8.5 Conscious Networks 81<br/>Summary 82<br/>Programming Assignment 82<br/>References 85<br/>associative memory<br/>41 Autocorrelators<br/>42 Heterocorrelators: Kosko's Discrete BAM 91<br/>4.3<br/>42 1 Addition and Deletion of Pattern Pairs 91<br/>4 2 1 . —<br/>422 Energy Function for BAM 92<br/>Wang et al.'s Multiple Training Encoding Strategy 95<br/>4.4 Exponential BAM 99<br/>4.4.1 Evolution Equations 99<br/>4.5 Associative Memory for Real-coded Pattern Pairs 101<br/>4.5.1 Input Normalization 101<br/>4.5.2 Evolution Equations 101<br/>4.6 Applications 105<br/>4.6.1 Recognition of Characters 105<br/>4.6.2 Fabric Defect Identification 107<br/>4.7 Recent Trends 110<br/>Summary 111<br/>Programming Assignment 111<br/>References 114<br/>ADAPTIVE RESONANCE THEORY<br/>5.1 Introduction 117<br/>5.1.1 Cluster Structure 117<br/>5.1.2 Vector Quantization 118<br/>5.1.3 Classical ART Networks 125<br/>5.1.4' Simplified ART Architecture 126<br/>5.2 ARTl 127<br/>5.2.1 Architecture of ARTl 128<br/>5.2.2 Special Features of ARTl Models 129<br/>5.2.3 ARTl Algorithm 133<br/>5.2.4 Illustration 135<br/>5.3 ART2 140<br/>5.3.1 Architecture of ART2 140<br/>5.3.2 ART2 Algorithm 141<br/>5.3.3 Illustration 144<br/>5.4 Applications 145<br/>5.4.1 Character Recognition Using ARTl 145<br/>5.4.2 Classification of Soil 146<br/>5.4.3 Prediction of Load from Yield Line Patterns of Elastic-Plastic<br/>Clamped Square Plate 147<br/>5.4.4 Chinese Character Recognition—Some Remarks 151<br/>5.5 Sensitivities of Ordering of Data 151<br/>Summary 152<br/>Programming Assignment 153<br/>Suggested Further Reading 153<br/>References 153<br/>FUZZY SET THEORY<br/>6.1 Fuzzy versus Crisp 157<br/>6.2 Crisp sets 159<br/>Part 2 FUZZY LOGIC<br/>6.2.1 Operations on Crisp Sets 161<br/>6.2.2 Properties of Crisp Sets 163<br/>6.2.3 Partition and Covering 166<br/>6.3 Fuzzy Sets 168<br/>6.3.1 Membership Function 169<br/>6.3.2 Basic Fuzzy Set Operations 171<br/>6.3.3 Properties of Fuzzy Sets 176<br/>6.4 Crisp Relations 179<br/>6.4.1 Cartesian Product 179<br/>6.4.2 Other Crisp Relations 180<br/>6.4.3 Operations on Relations 180<br/>6.5 Fuzzy Relations 182<br/>6.5.1 Fuzzy Cartesian Product 182<br/>6.5.2 Operations on Fuzzy Relations 183<br/>Summary 185<br/>Programming Assignment 186<br/>Suggested Further Reading 186<br/>Reference 186<br/>7 FUZZY SYSTEMS<br/>7.1 Crisp Logic 187<br/>7.1.1 Laws of Propositional Logic 189<br/>7.1.2 Inference in Propositional Logic 191<br/>7.2 Predicate Logic 193<br/>7.2.1 Interpretations of Predicate Logic Formula 195<br/>7.2.2 Inference in Predicate Logic 196<br/>7.3 Fuzzy Logic 198<br/>7.3.1 Fuzzy Quantifiers 201<br/>7.3.2 Fuzzy Inference 202<br/>lA Fuzzy Rule based System 204<br/>7.5 Defuzziflcation Methods 205<br/>7.6 Applications 210<br/>7.6.1 Greg Viot's Fuzzy Cruise Controller 210<br/>7.6.2 Air Conditioner Controller 216<br/>Summary 219<br/>Programming Assignment 220<br/>Suggested Further Reading 220<br/>References 220<br/>Part 3 GENETIC ALGORITHMS<br/>8 fundamentals OF GENETIC ALGORITHMS<br/>8.1 Genetic Algorithms: History 227<br/>8.2 Basic Concepts ^228<br/>8.2.1 Biological Background 228<br/>8.3 Creation of Offsprings 229<br/>8.3.1 Search Space<br/>8.4 Working Principle 230<br/>8.5 Encoding 230<br/>8.5.1 Binary Encoding 231<br/>8.5.2 Octal Encoding (0 to 7) 234<br/>8.5.3 Hexadecimal Encoding (0123456789ABCDEF) 234<br/>8.5.4 Permutation Encoding 235<br/>8.5.5 Value Encoding 236<br/>8.5.6 Tree Encoding 236<br/>8.6 Fitness Function 237<br/>8.7 Reproduction 242<br/>8.7.1 Roulette-wheel Selection 242<br/>8.7.2 Boltzmann Selection 245<br/>8.7.3 Tournament Selection 245<br/>8.7.4 Rank Selection 247<br/>8.7.5 Steady-state Selection 248<br/>8.7.6 Elitism 248<br/>8.7.7 Generation Gap and Steady-state Replacement 249<br/>Summary 250<br/>Programming Assignment 251<br/>References 252<br/>9 GENETIC MODELLING<br/>9.1 Inheritance Operators 253<br/>9.2 Cross Over 254<br/>9.2.1 Single-site Cross Over 254<br/>9.2.2 Two-point Cross Over 255<br/>9.2.3 Multi-point Cross Over 255<br/>9.2.4 Uniform Cross Over 256<br/>9.2.5 Matrix Cross Over (Two-dimensional Cross Over) 257<br/>9.2.6 Cross Over Rate 258<br/>9.3 Inversion and Deletion 259<br/>9.3.1 Inversion 259<br/>9.3.2 Deletion and Duplication 259<br/>9.3.3 Deletion and Regeneration 260<br/>9.3.4 Segregation 260<br/>9.3.5 Cross Over and Inversion 261<br/>9.4 Mutation Operator 261<br/>9.4.1 Mutation 261<br/>9.4.2 Mutation Rate P„ 262<br/>9.5 Bit-wise Operators 265<br/>9.5.1 One's Complement Operator 263<br/>9.5.2 Logical Bit-wise Operators 263<br/>9.5.3 Shift Operators 264<br/>9.6 Bit-wise Operators Used in GA 265<br/>9.7 Generational Cycle 265<br/>9.8 Convergence of Genetic Algorithm 271<br/>9.9 Applications 272<br/>9.9.1 Composite Laminates 272<br/>9.9.2 Constrained Optimization 277<br/>9.10 Multi-level Optimization 283<br/>9.11 Real Life Problem 284<br/>9.12 Differences and Similarities between GA and Other Traditional<br/>Methods 287<br/>9.13 Advances in GA 288<br/>Summary 291<br/>Programming Assignment 292<br/>Suggested Further Reading 292<br/>Some Useful Websites 293<br/>References 293<br/>Part 4 HYBRID SYSTEMS<br/>10 INTEGRATION OF NEURAL NETWORKS, FUZZY LOGIC, AND GENETIC<br/>ALGORITHMS<br/>10.1 Hybrid Systems 298<br/>10.1.1 Sequential Hybrid Systems 298<br/>10.1.2 Auxiliary Hybrid Systems 298<br/>10.1.3 Embedded Hybrid Systems 299<br/>10.2 Neural Networks, Fuzzy Logic, and Genetic Algorithms Hybrids 300<br/>10.2.1 Neuro-Fuzzy Hybrids 300<br/>10.2.2 Neuro-Genetic Hybrids 300<br/>10.2.3 Fuzzy-Genetic Hybrids 301<br/>10.3 Preview of the Hybrid Systems to be Discussed 301<br/>10.3.1 Genetic Algorithm based Backpropagation Network 302<br/>10.3.2 Fuzzy-Backpropagation Network 302<br/>10.3.3 Simplified Fuzzy ARTMAP 302<br/>10.3.4 Fuzzy Associative Memories 302<br/>10.3.5 Fuzzy Logic Controlled Genetic Algorithms 303<br/>Summary 303<br/>References 303<br/>11 genetic ALGORITHM BASED BACKPROPAGATION NETWORKS<br/>41.1 GA Based Weight Determination 306<br/>11.1.1 Coding 306<br/>11.1.2 Weight Extraction 308<br/>11.1.3 Fitness Function 309<br/>11.1.4 Reproduction 311<br/>If. 1.5 Convergence 313<br/>11.2 Applications 322<br/>11.2.1 K-factor Determination in Columns 322<br/>11.2.2 Electrical Load Forecasting 323<br/>Summary 325<br/>Programming Assignment 326<br/>Suggested Further Reading 326<br/>References 327<br/>12 FUZZY BACKPROPAGATION NETWORKS<br/>12.1 LR-type Fuzzy numbers 328<br/>12.1.1 Operations on LR-type Fuzzy Numbers 330<br/>12.2 Fuzzy Neuron 330<br/>12.3 Fuzzy BP Architecture 331<br/>12.4 Learning in Fuzzy BP 333<br/>12.5 Inference by Fuzzy BP 339<br/>12.6 Applications 347<br/>12.6.1 Knowledge Base Evaluation 348<br/>12.6.2 Earthquake damage Evaluation 353<br/>Summary 355<br/>Programming Assignment 356<br/>References 357<br/>13 SIMPLIFIED FUZZY ARTMAP<br/>13.1 Fuzzy ARTMAP: A Brief Introduction 358<br/>13.2 Simplified Fuzzy ARTMAP 359<br/>13.2.1 Input Normalization 360<br/>13.2.2 Output Node Activation 361<br/>13.3 Working of Simplified Fuzzy ARTMAP 364<br/>13.4 Application: Image Recognition 370<br/>13.4.1 Feature Extraction—Moment Based Invariants 372<br/>13.4.2 Computation of Invariants 375<br/>13.4.3 Structure of the Simplified Fuzzy ARTMAP Based<br/>Pattern Recognizer 380<br/>13.4.4 Experimental Study 381<br/>13.5 Recent Trends 384<br/>Summary 384<br/>Programming Assignment 385<br/>References 387<br/>14 FUZZY ASSOCIATIVE MEMORIES<br/>14.1 FAM—An Introduction 389<br/>14.2 Single Association FAM 390<br/>14.2.1 Graphical Method of Inference 392<br/>14.2.2 Correlation Matrix Encoding 393<br/>14.3 Fuzzy Hebb FAMs 395<br/>14.4 FAM Involving a Rule Base 400<br/>14.5 FAM Rules with Multiple Antecedents/Consequents 401<br/>14.5.1 Decomposition Rules 404<br/>14.6 Applications 406<br/>14.6.1 Balancing an Inverted Pendulum 406<br/>14.6.2 Fuzzy Truck Backer-upper System 411<br/>Summary 414<br/>Programming Assignment 415<br/>Suggested Further Reading 416<br/>References 416<br/>15 FUZZY LOGIC CONTROLLED GENETIC ALGORITHMS<br/>15.1 Soft Computing Tools 417<br/>15.1.1 Fuzzy Logic as a Soft Computing Tool 417<br/>15.1.2 Genetic Algorithm as a Soft Computing Tool 418<br/>15.2 Problem Description of Optimum Design 418<br/>15.3 Fuzzy Constraints 419<br/>15.4 Illustrations 420<br/>15.4.1 Optimization of the Weight of a Beam 420<br/>15.4.2 Optimal Mix Design for High Performance Concrete 422<br/>15.5 GA in Fuzzy Logic Controller Design 424<br/>15.6 Fuzzy Logic Controller 425<br/>15.6.1 Components of a Fuzzy Logic Controller (FLC) 425<br/>15.6.2 Fuzzy IF-THEN Rules 426<br/>15.7 FLC-GA Based Structural Optimization 429<br/>15.8 Applications 429<br/>15.8.1 Optimum Truss 429<br/>15.8.2 112 Bar Dome Space Truss 431<br/>Summary 432<br/>Programming Assignment 433<br/>Suggested Further Reading 435<br/>References 435<br/>
650 ## - SUBJECT
Keyword Neural network
650 ## - SUBJECT
Keyword Fuzzy logic
650 ## - SUBJECT
Keyword Computer algorithms
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type GN Books
Holdings
Withdrawn status Lost status Damaged status Not for loan Home library Current library Shelving location Date acquired Full call number Accession number Date last seen Date last checked out Koha item type
        Central Library, Sikkim University Central Library, Sikkim University General Book Section 22/06/2016 006.32 RAJ/N P35935 02/03/2023 02/02/2023 General Books
SIKKIM UNIVERSITY
University Portal | Contact Librarian | Library Portal

Powered by Koha