, Volume 15, Issue 4–5, pp 263–281 | Cite as

Stochastic automata and learning systems

  • M A L Thathachar
Learning Automata And Neural Networks


We consider stochastic automata models of learning systems in this article. Such learning automata select the best action out of a finite number of actions by repeated interaction with the unknown random environment in which they operate. The selection of an action at each instant is done on the basis of a probability distribution which is updated according to a learning algorithm. Convergence theorems for the learning algorithms are available. Moreover the automata can be arranged in the form of teams and hierarchies to handle complex learning problems such as pattern recognition. These interconnections of learning automata could be regarded as artificial neural networks.


Stochastic automata learning systems artificial neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Banerjee S 1989On stochastic relaxation paradigms for computational vision, PhD thesis, Electrical Engineering Department, Indian Institute of Science, BangaloreGoogle Scholar
  2. Bush R R, Mosteller F 1958Stochastic models for learning (New York: John Wiley and Sons)Google Scholar
  3. Lakshmivarahan S 1981Learning algorithms — theory and applications (New York: Springer Verlag)MATHGoogle Scholar
  4. Lakshmivarahan S, Thathachar M A L 1973 Absolutely expedient learning algorithms for stochastic automata.IEEE Trans. Syst., Man Cybern. SMC-3: 281–283MathSciNetGoogle Scholar
  5. Mason L G, Gu X D 1986 Learning automata models for adaptive flow control in packet-switching networks. InAdaptive and learning systems (ed.) K S Narendra (New York: Plenum)Google Scholar
  6. Mukhopadhyay S, Thathachar M A L 1989 Associative learning of Boolean functions.IEEE Trans. Syst. Man Cybern. SMC-19: 1008–1015CrossRefMathSciNetGoogle Scholar
  7. Narendra K S, Mars P 1983 The use of learning algorithms in telephone traffic routing — A methodology,Automatica 19: 495–502MATHCrossRefGoogle Scholar
  8. Narendra K S, Thathachar M A L 1989Learning automata — an introduction (Englewood Cliffs,NJ: Prentice Hall)Google Scholar
  9. Ramakrishnan K R 1982Hierarchical systems and cooperative games of learning automata, PhD thesis, Indian Inst. Sci. BangaloreGoogle Scholar
  10. Sastry P S, Banerjee S, Ramakrishnan K R 1988 A local cooperative processing model for low level vision.Indo-US Workshop on Systems and Signal Processing (ed.) N Viswanadham (New Delhi: Oxford & IBH)Google Scholar
  11. Shapiro I J, Narendra K S 1969 Use of stochastic automata for parameter self-optimization with multimodal performance criteria.IEEE Trans. Syst. Sci. Cybern. SSC-5: 352–360CrossRefGoogle Scholar
  12. Thathachar M A L, Sastry P S 1985 A new approach to the design of reinforcement schemes for learning automata.IEEE Trans. Syst., Man Cybern. SMC-15: 168–175MathSciNetGoogle Scholar
  13. Thathachar M A L, Sastry P S 1986 Relaxation labeling with learning automata.IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8: 256–268Google Scholar
  14. Thathachar M A L, Sastry P S 1987 Learning optimal discriminant functions through a cooperative game of automata.IEEE Trans. Syst., Man Cybern. SMC-17: 73–85CrossRefMathSciNetGoogle Scholar
  15. Tsetlin M L 1973Automaton theory and modeling of biological systems (New York: Academic Press)Google Scholar
  16. Williams R J 1988 Toward a theory of reinforcement — learning connectionist systems, Technical Report, NU-CCS-88-3, College of Computer Science, Northeastern University, Boston, MAGoogle Scholar

Copyright information

© the Indian Academy of Sciences 1990

Authors and Affiliations

  • M A L Thathachar
    • 1
  1. 1.Department of Electrical EngineeringIndian Institute of ScienceBangaloreIndia

Personalised recommendations