Learning Optimal Discriminant Functions through a Cooperative Game of Automata

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.

[1]  J. Neumann,et al.  The Theory of Games and Economic Behaviour , 1944 .

[2]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[3]  Stephen S. Yau,et al.  Design of Pattern Classifiers with the Updating Property Using Stochastic Approximation Techniques , 1968, IEEE Transactions on Computers.

[4]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[5]  Jack Sklansky,et al.  Training a One-Dimensional Classifier to Minimize the Probability of Error , 1972, IEEE Trans. Syst. Man Cybern..

[6]  R. Radner,et al.  Economic theory of teams , 1972 .

[7]  K. Narendra.  Competitive and Cooperative Games of Variable-Structure Stochastic Automata , 1973 .

[8]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[9]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[10]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[11]  Kumpati S. Narendra,et al.  Learning Automata - A Survey , 1974, IEEE Trans. Syst. Man Cybern..

[12]  J. Sklansky,et al.  An adaptive nonparametric linear classifier , 1976, Proceedings of the IEEE.

[13]  Hai Do-Tu,et al.  Learning Algorithms for Nonparametric Solution to the Minimum Error Classification Problem , 1978, IEEE Transactions on Computers.

[14]  S. Lakshmivarahan,et al.  Learning Algorithms Theory and Applications , 1981 .

[15]  M. Thathachar,et al.  A Hierarchical System of Learning Automata , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  P. R. Srikantakumar,et al.  A LEARNING MODEL FOR ROUTING IN TELEPHONE NETWORKS , 1982 .

[17]  K. R. Ramakrishnan,et al.  Hierarchical Systems and Cooperative Games of Learning Automata , 1982 .

[18]  K. R. Ramakrishnan,et al.  A cooperative game of a pair of learning automata , 1984, Autom..

[19]  P. Anandan,et al.  Pattern-recognizing stochastic learning automata , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[20]  A G Barto,et al.  Learning by statistical cooperation of self-interested neuron-like computing elements. , 1985, Human neurobiology.

[21]  M. A. L. THATHACHAR,et al.  A new approach to the design of reinforcement schemes for learning automata , 1985, IEEE Transactions on Systems, Man, and Cybernetics.