Learning Optimal Discriminant Functions through a Cooperative Game of Automata
- 1 January 1987
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. 17 (1) , 73-85
- https://doi.org/10.1109/tsmc.1987.289334
Abstract
The problem of learning correct decision rules to minimize the probability of misclassification is a long-standing problem of supervised learning in pattern recognition. The problem of learning such optimal discriminant functions is considered for the class of problems where the statistical properties of the pattern classes are completely unknown. The problem is posed as a game with common payoff played by a team of mutually cooperating learning automata. This essentially results in a probabilistic search through the space of classifiers. The approach is inherently capable of learning discriminant functions that are nonlinear in their parameters also. A learning algorithm is presented for the team and convergence is established. It is proved that the team can obtain the optimal classifier to an arbitrary approximation. Simulation results with a few examples are presented where the team learns the optimal classifier.Keywords
This publication has 14 references indexed in Scilit:
- Pattern-recognizing stochastic learning automataIEEE Transactions on Systems, Man, and Cybernetics, 1985
- A new approach to the design of reinforcement schemes for learning automataIEEE Transactions on Systems, Man, and Cybernetics, 1985
- A cooperative game of a pair of learning automataAutomatica, 1984
- A Learning Model for Routing in Telephone NetworksSIAM Journal on Control and Optimization, 1982
- A Hierarchical System of Learning AutomataIEEE Transactions on Systems, Man, and Cybernetics, 1981
- An adaptive nonparametric linear classifierProceedings of the IEEE, 1976
- Learning Automata - A SurveyIEEE Transactions on Systems, Man, and Cybernetics, 1974
- Competitive and Cooperative Games of Variable-Structure Stochastic AutomataJournal of Cybernetics, 1973
- Design of Pattern Classifiers with the Updating Property Using Stochastic Approximation TechniquesIEEE Transactions on Computers, 1968
- PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMSPublished by Defense Technical Information Center (DTIC) ,1961