Computational Intelligence: An Introduction

Computational intelligence as a new development paradigm of intelligent systems has resulted from a synergy between neural networks, fuzzy sets, and genetic computations. This emerging area, even at its very earliest stage, has already attracted the attention of top researchers and practitioners. Computational Intelligence: An Introduction delivers a highly readable and fully systematic treatment of the fundamentals of CI, along with the clear presentation of sound and comprehensive analysis and design practices. This text pulls together much of the scattered information written about this emerging field. Most publications dealing with CI are highly specialized and concentrate narrowly on the symbiosis between NN, FS, and GAs. Computational Intelligence: An Introduction bridges the gap between all three areas and CI. This is an important text for anyone engaged in any way with genetic algorithms, fuzzy sets, neural networks, and computational intelligence.

Table of Contents:
Chapter 1. Preliminaries Computational Intelligence: Its Inception and Research Agenda Organization and Readership References Chapter 2. Neural Networks and Neurocomputing Introduction Generic Models of Computational Neurons Architectures of Neural Networks - A Basic Taxonomy Learning in Neural Networks Selected Classes of Learning Methods Generalization Abilities of Neural Networks Enhancements of Gradient-Based Learning in Neural Networks Concluding Remarks Problems References Chapter 3. Fuzzy Sets Introduction Basic Definition Types of Membership Functions Characteristics of a Fuzzy Set Membership Function Determination Fuzzy Relations Set Theory Operations and Their Properties Triangular Norms Triangular Norms as the Models of Operations on Fuzzy Sets Information-Based Characteristics of Fuzzy Sets Matching Fuzzy Sets Numerical Representation of Fuzzy Sets Rough Sets Rough Sets and Fuzzy Sets Shadowed Sets The Frame of Cognition Probability and Fuzzy Sets Hybrid Fuzzy-Probabilistic Models of Uncertainty Conclusions Problems References Chapter 4. Computations with Fuzzy Sets Introductory Remarks The Extension Principle Fuzzy Numbers Fuzzy Rule-Based Computing Fuzzy Controller and Fuzzy Control Rule-Based Systems with Nonmonotonic Operations Conclusions Problems References Chapter 5. Evolutionary Computing Introduction Gradient-Based and Probabilistic Optimization as Examples of Single-Point Search Techniques Genetic Algorithms - Fundamentals and a Basic Algorithm Schemata Theorem - A Conceptual Backbone of GAs From Search Space to GA Search Space Exploration and Exploitation of the Search Space Experimental Studies Classes of Evolutionary Computation Conclusions Problems References Chapter 6. Fuzzy Neural Systems Introduction Neurocomputing in Fuzzy Set Technology Fuzzy Sets in the Technology of Neurocomputing Fuzzy Sets in the Preprocessing and Enhancements of Training Data Uncertainty Representation in Neural Networks Neural Calibration of Membership Functions Knowledge-Based Learning Schemes Linguistic Interpretation of Neural Networks Hybrid Fuzzy Neural Computing Structures Conclusions Problems References Chapter 7. Fuzzy Neural Networks Logic-Based Neurons Logic Neurons and Fuzzy Neural Networks with Feedback Referential Logic-Based Neurons Learning in Fuzzy Neural Networks Case Studies Conclusions Problems References Chapter 8. CI Systems Introduction Fuzzy Encoding in Evolutionary Computing Fuzzy Crossover Operations Fuzzy Metarules in Genetic Computing Relational Structures and Their Optimization The Satisfiability Problem Evolutionary Rule-Based Modeling of Analytical Relationships Genetic Optimization of Neural Networks Genetic Optimization of Rule-Based Systems Conclusions Problems References Index