Stochastic automata and learning systems
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.
KeywordsStochastic automata learning systems artificial neural networks
Unable to display preview. Download preview PDF.
- Banerjee S 1989On stochastic relaxation paradigms for computational vision, PhD thesis, Electrical Engineering Department, Indian Institute of Science, BangaloreGoogle Scholar
- Bush R R, Mosteller F 1958Stochastic models for learning (New York: John Wiley and Sons)Google Scholar
- 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
- Narendra K S, Thathachar M A L 1989Learning automata — an introduction (Englewood Cliffs,NJ: Prentice Hall)Google Scholar
- Ramakrishnan K R 1982Hierarchical systems and cooperative games of learning automata, PhD thesis, Indian Inst. Sci. BangaloreGoogle Scholar
- 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
- Thathachar M A L, Sastry P S 1986 Relaxation labeling with learning automata.IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8: 256–268Google Scholar
- Tsetlin M L 1973Automaton theory and modeling of biological systems (New York: Academic Press)Google Scholar
- 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