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.
For graduate students in control theory and statistics and for practising control engineers.
Contents. Preface. Notations. Introduction. Basic Notions and Definitions. Introduction. Controlled finite system. Control strategies. Dynamic characteristics of controlled finite system. Classification of controlled finite systems and their structures. Adaptive strategies and learning automata. Classification of problems of adaptive control of finite systems. Reinforcement Schemes for Average Loss Function Minimization. Introduction. Adaptive control of static systems. Adaptive control of static systems and linear programming problem. Reinforcement schemes. Properties of reinforcement schemes. Behaviour of Learning Automata for Different Reinforcement Schemes. Introduction. Reinforcement scheme of Narendra-Shapiro. Reinforcement scheme of Luce and Varshavskii-Vorontsova. Bush-Mosteller reinforcement scheme. Projectional stochastic approximation algorithm. Conclusion. Multilevel Systems of Automata. Introduction. Hierarchical systems. The connection between two-level adaptive control and bilinear programming problem. Two-level hierarchical system of learning automata. Two-level hierarchical system of learning automata using a projectional stochastic approximation algorithm. Two-level hierarchical system with transmission of current information to the lower level. Multilevel hierarchical learning system. Conclusion. Multimodal Function Optimization Using Learning Automata. Introduction. Optimization using a single learning automata. Optimization using a two-level hierarchical system of learning automata. Optimization using a multilevel learning automata system. Conclusion. Applications of Learning Automata. Introduction. Practical aspects. Multilevel learning control of a drying furnace. Hierarchical learning control of an absorption column. Learning control of an evaporator. Adaptive choice of cyclic code in communications systems. Optimization of multimodal functions (without constraints). Optimization in presence of constraints. Application of learning automaton to neural network synthesis. Conclusion. Nomenclature. References. Appendix. Index.
- No. of pages:
- © Pergamon 1994
- 5th October 1994
- eBook ISBN:
E.N.S.I.G.C., Toulouse, France
Center of Research and Advanced Education of the National Polytechnic Institute, Mexico