Networks of Learning Automata

Techniques for Online Stochastic Optimization

  • M. A. L. Thathachar
  • P. S. Sastry

Table of contents

  1. Front Matter
    Pages i-xv
  2. M. A. L. Thathachar, P. S. Sastry
    Pages 1-49
  3. M. A. L. Thathachar, P. S. Sastry
    Pages 51-103
  4. M. A. L. Thathachar, P. S. Sastry
    Pages 105-138
  5. M. A. L. Thathachar, P. S. Sastry
    Pages 139-176
  6. M. A. L. Thathachar, P. S. Sastry
    Pages 177-204
  7. M. A. L. Thathachar, P. S. Sastry
    Pages 205-222
  8. M. A. L. Thathachar, P. S. Sastry
    Pages 223-225
  9. Back Matter
    Pages 227-268

About this book

Introduction

Networks of Learning Automata: Techniques for Online Stochastic Optimization is a comprehensive account of learning automata models with emphasis on multiautomata systems. It considers synthesis of complex learning structures from simple building blocks and uses stochastic algorithms for refining probabilities of selecting actions. Mathematical analysis of the behavior of games and feedforward networks is provided. Algorithms considered here can be used for online optimization of systems based on noisy measurements of performance index. Also, algorithms that assure convergence to the global optimum are presented. Parallel operation of automata systems for improving speed of convergence is described. The authors also include extensive discussion of how learning automata solutions can be constructed in a variety of applications.

Keywords

Computer Vision Performance Simulation Stochastic Approximation Stochastic Optimization algorithms calculus cognition communication intelligence learning optimization organization proving supervised learning

Authors and affiliations

  • M. A. L. Thathachar
    • 1
  • P. S. Sastry
    • 1
  1. 1.Dept. of Electrical EngineeringIndian Institute of ScienceBangaloreIndia

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4419-9052-5
  • Copyright Information Kluwer Academic Publishers 2004
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-4775-0
  • Online ISBN 978-1-4419-9052-5
  • About this book