상세정보

For control engineers and graduate students of control theory, provides a systematic treatment of learning automata, with a wide variety of ideas and methods that can be used in learning systems and enough theoretical material to allow the user to understand why and how they can be used. Among the example applications are the multilevel learning control of a drying furnace, the adaptive choice of cyclic code in communications systems, and neural network synthesis. Annotation copyright Book News, Inc. Portland, Or.

정보제공 :

CONTENTS
Contents = ⅴ
Preface = ⅸ
Notations = 1
Introduction = 3
1 basic Notions and Definitions = 6
 Introduction = 6
 1 Controlled finite system = 7
 2 Control strategies = 7
 3 Dynamic characteristics of controlled finite system = 10
 4 Classification of controlled finite systems and their structures = 11
 5 Adaptive strategies and learning automata = 15
 6 Classification of Problems of adaptive control of finite systems = 16
2 Reinforcement Schemes of Average Loss Function Minimization = 19
 Introduction = 19
 1 Adaptive control of static systems = 20
 2 Adaptive control of static systems and linear programming problem = 24
 3 Reinforcement schemes = 28
 4 Properties of reinforcement schemes = 32
3 Behaviour of Learning Automata for Different Reinforcement Schemes = 40
 Introduction = 40
 1 Reinforcement scheme of Narendra-Shapiro = 41
 2 Reinforcement scheme of Luce and Varshavskii-Vorontsova = 52
 3 Bush-Mosteller reinforcement scheme = 59
 4 Projectional stochastic approximation algorithm = 67
 Conclusion = 75
4 Multilevel Systems of Automata = 77
 Introductin = 77
 1 Hierarchical systems = 77
 2 The connection between two-level adaptive control and bilinear programming problem = 78
 3 Two-level hierarchical system of learning automata = 82
 4 Two-level hierarchical system of learning automata using a projectional stochastic approximation algorithm = 93
 5 Two-level hierarchical system with transmission of current information to the lower level = 100
 6 Multilevel hierarchical learning system = 108
 Conclusion = 119
5 Multimodal function Optimization Using Learning Automata = 120
 Introduction = 120
 1 Optimization using a single learning automata = 121
 2 Optimization using a two-level hierarchical system of learning automata = 128
 3 Optimization using a multilevel learning automata system = 136
 Conclusion = 143
6 Applications of Learning Automata = 144
 Introduction = 144
 1 Practical aspects = 148
 2 Multilevel learning control of a drying furnace = 150
 3 Hierarchical learning control of an absorption column = 163
 4 Learning control of an evaporator = 173
 5 Adaptive choice of cyclic code in communications systems = 178
 6 Optimization of multimodal functions (without constraints) = 182
 7 Optimization in presence of constraints = 186
 8 Application of learning automaton to neural network synthesis = 199
 Conclusion = 203
 Nomenclature = 204
References = 206
Appendix = 215
Index = 224