文件名称：Computational Intelligence:An Introduction
文件大小：12.14MB
文件格式：TGZ
更新时间：2011-10-27 05:55:36
Computational Intelligence
Chapter 1—Preliminaries 1.1. Computational Intelligence: its inception and research agenda 1.2. Organization and readership 1.3. References Chapter 2—Neural Networks and Neurocomputing 2.1. Introduction 2.2. Generic models of computational neurons 2.3. Architectures of neural networks - a basic taxonomy 2.3.1. Radial Basis function neural networks 2.4. Learning in neural networks 2.4.1. Neural networks as universal approximators 2.4.2. Generic modes of learning in neural networks 2.4.3. Performance indexes in training of neural networks 2.5. Selected classes of learning methods 2.5.1. Gradient-based optimization of multivariable functions 2.5.2. Perceptron learning rule 2.5.3. Delta learning rule 2.5.4. Backpropagation learning 2.5.5. Hebbian learning 2.5.6. Competitive learning 2.5.7. Self-organizing maps 2.5.8. Learning in presence directly and indirectly labeled patterns 2.6. Generalization abilities of neural networks 2.7. Enhancements of gradient-based learning in neural networks 2.8. Concluding remarks 2.9. Problems 2.10. References Chapter 3—Fuzzy Sets 3.1. Introduction 3.2. Basic definition 3.3. Types of membership functions 3.4. Characteristics of a fuzzy set 3.5. Membership function determination 3.5.1. Horizontal method of membership estimation 3.5.2. Vertical method of membership estimation 3.5.3. Pairwise comparison method of membership function estimation 3.5.4. Problem specification-based membership determination 3.5.5. Membership estimation as a problem of parametric optimization 3.6. Fuzzy relations 3.7. Set theory operations and their properties 3.8. Triangular norms 3.9. Triangular norms as the models of operations on fuzzy sets 3.10. Information-based characteristics of fuzzy sets 3.10.1. Entropy measure of fuzziness 3.10.2. Energy measure of fuzziness 3.10.3. Specificity of a fuzzy set 3.11. Matching measures 3.11.1. Possibility and necessity measures 3.11.2. Compatibility measure 3.12. Numerical representation of fuzzy sets 3.13. Rough sets 3.14. Rough sets and fuzzy sets 3.15. Shadowed sets 3.16. The frame of cognition 3.16.1. Basic definition 3.16.2. Main properties 3.16.3. Approximation aspects of the frame of cognition 3.16.4. Robustness properties of the frame of cognition 3.17. Probability and fuzzy sets 3.18. Hybrid fuzzy-probabilistic models of uncertainty 3.19. Conclusions 3.20. Problems 3.21. References Chapter 4—Computations with Fuzzy Sets 4.1. Introductory remarks 4.2. The extension principle 4.3. Fuzzy numbers 4.3.1. Basic characteristics 4.3.2. Computing with fuzzy numbers 4.3.3. Accumulation of fuzziness in computing with fuzzy numbers 4.4. Fuzzy rule-based computing 4.4.1. Rules with fuzzy sets 4.4.2. A design of fuzzy rule - based systems 4.4.3. Fuzzy Hebbian learning and associative memory as a realization of rule-based systems 4.5. Fuzzy controller and fuzzy control 4.5.1. Generic concept of fuzzy control 4.5.2. Design principles of the fuzzy controller 4.5.3. Numerical experiments 4.5.4. Fuzzy scheduler 4.6. Rule-based systems with nonmonotonic operations 4.6.1. Nonmonotonic AND and OR operations: a generalization 4.6.2. Estimation problem of the default fuzzy set 4.6.3. Approximate reasoning with defaults 4.7. Conclusions 4.8. Problems 4.9. References Chapter 5—Evolutionary Computing 5.1. Introduction 5.2. Gradient-based and probabilistic optimization as examples of single-point search techniques 5.3. Genetic algorithms - fundamentals and a basic algorithm 5.4. Schemata Theorem - a conceptual backbone of GAs 5.5. From search space to GA search space 5.5.1. Gray coding 5.5.2. Floating point coding 5.6. Exploration and exploitation of the search space 5.7. Experimental studies 5.8. Classes of evolutionary computation 5.8.1. Evolutionary Strategies 5.8.2. Evolutionary Programming 5.8.3. Genetic Programming 5.9. Conclusions 5.10 Problems 5.11. References Chapter 6—Fuzzy Neural Systems 6.1. Introduction 6.2. Neurocomputing in fuzzy set technology 6.3. Fuzzy sets in the technology of neurocomputing 6.4. Fuzzy sets in the preprocessing and enhancements of training data 6.4.1. Nonlinear data normalization 6.4.2. Variable processing resolution - fuzzy receptive fields 6.5. Uncertainty representation in neural networks 6.6. Neural calibration of membership functions 6.6.1. The Optimization Algorithm 6.6.2. Neural network realization of the nonlinear mapping 6.7. Knowledge-based learning schemes 6.7.1. Metalearning and fuzzy sets 6.7.2. Fuzzy clustering in revealing relationships within data 6.7.2.1. Fuzzy perceptron 6.7.2.2. Conditional (context-sensitive) clustering as a preprocessing phase in neural networks 6.8. Linguistic interpretation of neural networks 6.8.1. From neural networks to rule-based systems 6.8.2. Linguistic Interpretation of self-organizing maps 6.9. Hybrid fuzzy neural computing structures 6.9.1. Architectures of hybrid fuzzy neural systems 6.9.2. Temporal aspects of interaction in fuzzy-neural systems 6.10. Conclusions 6.11. Problems 6.12. References Chapter 7—Fuzzy Neural Networks 7.1. Logic-based neurons 7.1.1. Aggregative OR and AND logic neurons 7.1.2. OR/AND neurons 7.1.3. Conceptual and computational augmentations of fuzzy neurons 7.1.3.1. Representing inhibitory information 7.1.3.2. Computational enhancements of the neurons 7.2. Logic neurons and fuzzy neural networks with feedback 7.3. Referential logic-based neurons 7.4. Learning in fuzzy neural networks 7.4.1. Learning policies for parametric learning in fuzzy neural networks 7.4.2. Performance index 7.4.3. Interpretation of fuzzy neural networks 7.5. Case studies 7.5.1. Logic filtering 7.5.2. Minimization of multiple output two-valued combinational systems 7.5.3. FNN as a model of approximate reasoning 7.5.4. Sensor fusion via fuzzy neurons 7.6. Conclusions 7.7. Problems 7.8. References Chapter 8—CI systems 8.1. Introduction 8.2. Fuzzy encoding in evolutionary computing 8.2.1. Direct methods of fuzzy encoding 8.2.2. Weak encoding with fuzzy sets 8.3. Fuzzy crossover operations 8.4. Fuzzy metarules in genetic computing 8.5. Relational structures and their optimization 8.5.1. Image compression as a problem of relation reduction 8.5.2. GA-optimized data mining 8.6. The Satisfiability Problem 8.7. Evolutionary rule-based modeling of analytical relationships 8.8. Genetic optimization of neural networks 8.8.1. Parametric optimization of neural networks 8.8.2. Fuzzy genetic optimization of neural networks 8.9. Genetic optimization of rule-based systems 8.10. Conclusions 8.11. Problems 8.12. References Index