Introduction to neural networks, fuzzy logic & genetic algorithms: theory and applications/ Sudarshan K. Valluru and T. Nageswara Rao

Include bibliography

1. INTRODUCTION TO NEURAL NETWORKS
1.1 Introduction 2
1.2 Humcins Versus Computers 2
1.3 Structure of the Brain .2
1.4 Organization of the Brain 4
1.5 Learning Methodologies in Biological Systems 4
1.6 Basic Neuron Modeling 4
1.7 Computer Versus Biological Neural System 6
1.8 Artificial Neuron Modeling 7
1.9 Characteristics of Artificial Neural Networks 12
1.10 Historical Developments 13
1.11 Potential Applications of Neural Networks 14
1.12 Points to Remember 14
Questions 16
2. ESSENTIALS OF ARTIFICIAL NEURAL NETWORKS
2.1 Introduction 18
2.2 Neural Information Processing 18
2.3 Model of an Artificial Neuron 19
2.4 Operation of an Artificial Neuron and Models of Static and Dynamic
Artificial Neurons (Adaptive Function Estimators) 19
2.5 Neuron Activation Fimctions 21
2.6 Artificial Neural Network Architectures 23
2.7 Taxonomy of an ANN 25
2.8 Neural Djmamics 26
2.9 T)rpes of Applications 31
2.10 Points to Remember 32
Questions 33
3. SINGLE LAYER FEED-FORWARD NEURAL NETWORKS
3.1 Introduction 36
3.2 Generalized Perceptron Model 36
3.3 Perceptron Convergence Theorem 38
3.4 Discrete Single Layer Perceptron 41
3.5 Discrete Single Layer Perceptron Training Algorithm 44
3.6 Continuous Single Layer Perceptron Artificial Neuron Modeling 45
3.7 Continuous Single Layer Perception Training Algorithm 47
3.8 Multi-category Single Layer Perception 47
3.9 Multi-category Single Layer Perception Training Algorithm 51
3.10 Limitations
3.11 Points to Remember
Questions
4. MULTILAYER FEED FORWARD NEURAL NETWORKS
4.1 Introduction
4.2 Credit Assignment Problem
4.3 The New Model
4.4 The Generalized Delta Rule
4.5 Derivation of the Back Propagation (BP) Training Algorithm 60
4.6 Summary of the Back Propagation Algorithm 63
4.7 Kolmogorov's Theorem ^
4.8 Learning Difficulties
4.9 Applications
4.10 Points to Remember
Questions
5. ASSOCIATIVE MEMORIES
5.1 Introduction
5.2 Paradigms of Associative Memory
5.3 Pattern Mathematics
5.4 Hebbian Learning
5.5 General Concepts of Associative Memory
5.6 Bidirectional Associative Memories
5.7 Architecture of a Hopfield Network
5.8 Points to Remember
Questions
6. CLASSICAL AND FUZZY SETS
6.1 Introduction
6.2 The Need for a Fuzzy Theory and its Advantages
6.3 Classical Sets (Crisp Sets) and Operations on Classical Sets
6.4 Fuzzy Sets and Operations on Fuzzy Sets
6.5 Membership Functions (MFs)
6.6 Points to Remember
Questions
7. FUZZY LOGIC SYSTEM COMPONENTS
7.1 Introduction to Fuzzification
7.2 Membership Value Assignment
7.3 Generation of Rules and Decision Making System
7.4 Inference Methods

7.5 Configuration of a Fuzzy Logic Controller (FLC) 143
7.6 Diefuzzification Methods 152
7.7 Design Procedure of a Fuzzy Logic Controller 154
7.8 Analog Design Approach to a Simple Fuzzy Computer 156
7.9 Points to Remember 160
Questions 161
8. APPLICATIONS OF ANNs AND FUZZY LOGIC
8.1 Introduction 164
8.2 Process Identification arid Control 164
8.3 Fault Diagnosis 167
8.4 Load Forecasting Using an ANN 172
8.5 Applications of ANNs in Renewable Energy Systems 179
8.6 Applicationsof ANNs in Other Energy Systems 179
8.7 Applications of ANNs in Forecasting and Prediction 181
8.8 Fuzzy Logic Control 181
8.9 Applications of Fuzzy Logic Control 183
8.10 Points to Remember 190
Questions 191
9. NON-TRADITIONAL OPTIMIZED ALGORITHMS-GENETIC ALGORITHM
9.1 Introduction to Genetic Algorithms 194
9.2 Basic Terminology of Biology and Genetic Algorithms 195
9.3 Comparison between Genetic Algorithms and Other Traditional Algorithms 196
9.4 Overview of Genetic Algorithms 196
9.5 Lybrinthinism in Optimization 197
9.6 Generalized Steps of a Genetic Algorithm 198
9.7 The Modified Genetic Algorithm 207
9.8 Applications of Genetic Algorithms in Engineering Design 209
9.9 Current and Future Trends of Optimized Evolutionary Algorithms 213
9.10 Points to Remember
Questions '