Najim / Poznyak Learning Automata

Theory and Applications
1. Auflage 2014
ISBN: 978-1-4832-9940-2
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 236 Seiten, Web PDF

Learning systems have made a significant impact on all areas of engineering problems. They are attractive methods for solving many problems which are too complex, highly non-linear, uncertain, incomplete or non-stationary, and have subtle and interactive exchanges with the environment where they operate. The main aim of the book is to give a systematic treatment of learning automata and to produce a guide to a wide variety of ideas and methods that can be used in learning systems, including enough theoretical material to enable the user of the relevant techniques and concepts to understand why and how they can be used. The book also contains the materials that are necessary for the understanding and development of learning automata for different purposes such as processes identification, optimization and control. Learning Automata: Theory and Applications may be recommended as a reference for courses on learning automata, modelling, control and optimization. The presentation is intended both for graduate students in control theory and statistics and for practising control engineers.

Autoren/Hrsg.

Najim, K.

Poznyak, A. S.

Inhaltsverzeichnis

1;Front Cover
;1
2;Learning Automata: Theory and Applications;4
3;Copyright Page
;5
4;Table of Contents
;6
5;Preface;10
6;Notations;14
7;Introduction;16
8;Chapter 1. Basic Notions and Definitions
;19
8.1;Introduction;19
8.2;1 Controlled finite system;20
8.3;2 Control strategies;20
8.4;3 Dynamic characteristics of controlled finite system;23
8.5;4 Classification of controlled finite systems and their structures;24
8.6;5 Adaptive strategies and learning automata;28
8.7;6 Classification of problems of adaptive control of finite systems;29
9;Chapter 2. Reinforcement Schemes for Average Loss Function Minimization;32
9.1;Introduction;32
9.2;1 Adaptive control of static systems;33
9.3;2 Adaptive control of static systems and linear programming problem;37
9.4;3 Reinforcement schemes;41
9.5;4 Properties of reinforcement schemes;45
10;Chapter 3. Behaviour of Learning Automata for Different Reinforcement Schemes;53
10.1;Introduction;53
10.2;1 Reinforcement scheme of Narendra-Shapiro;54
10.3;2 Reinforcement scheme of Luce and Varshavskii-Vorontsova;65
10.4;3 Bush-Mosteller reinforcement scheme;72
10.5;4 Projectional stochastic approximation algorithm;80
10.6;Conclusion;88
11;Chapter 4. Multilevel Systems of Automata;90
11.1;Introduction;90
11.2;1 Hierarchical systems;90
11.3;2 The connection between two-level adaptive control and bilinear programming problem;91
11.4;3 Two-level hierarchical system of learning automata;95
11.5;4 Two-level hierarchical system of learning automata using a projectional stochastic approximation algorithm;106
11.6;5 Two-level hierarchical system with transmission of current information to the lower level;113
11.7;6 Multilevel hierarchical learning system;121
11.8;Conclusion;132
12;Chapter 5. Multimodal Function Optimization Using Learning Automata;133
12.1;Introduction;133
12.2;1 Optimization using a single learning automata;134
12.3;2 Optimization using a two-level hierarchical system of learning automata;141
12.4;3 Optimization using a multilevel learning automata system;149
12.5;Conclusion;156
13;Chapter 6. Applications of Learning Automata;157
13.1;Introduction;157
13.2;1 Practical aspects;161
13.3;2 Multilevel learning control of a drying furnace;163
13.4;3 Hierarchical learning control of an absorption column;176
13.5;4 Learning control of an evaporator;186
13.6;5 Adaptive choice of cyclic code in communications systems;191
13.7;6 Optimization of multimodal functions (without constraints;195
13.8;7 Optimization in presence of constraints;199
13.9;8 Application of learning automaton to neural network synthesis;212
13.10;Conclusion;216
13.11;Nomenclature;217
14;References;219
15;Appendix;228
16;Index;237