Abstract
This paper considers the problem of learning optimal discriminant functions for pattern classification. The criterion of optimality is minimising the probability of misclassification. No knowledge of the statistics of the pattern classes is assumed and the given classified sample may be noisy. We present a comprehensive review of algorithms based on the model of cooperating systems of learning automata for this problem. Both finite action set automata and continuous action set automata models are considered. All algorithms presented have rigorous convergence proofs. We also present algorithms that converge to global optimum. Simulation results are presented to illustrate the effectiveness of these techniques based on learning automata.
Similar content being viewed by others
References
Aluffi-Pentini F, Parisi V, Zirilli F 1985 Global optimisation and stochastic differential equations.J. Optim. Theory Appl. 47: 1–26
Barto A G 1985 Learning by statistical cooperation of self-interested neuron-like computing elements. COINS Tech. Report. 81-11, Univ. of Massachusetts, Amherst, MA
Barto A G, Anandan P 1985 Pattern-recognizing stochastic learning automata.IEEE Trans. Syst., Man Cybern. 15: 360–374
Baum E, Haussler D L 1989 What sized net gives valid generalisation.Neural Comput. 1: 151–160
Blum J R 1954 Multidimensional stochastic approximation methods.Ann. Math. Stat. 25: 737–744
Blumer A, Ehrenfeucht A, Haussler D L, Warmuth M K 1989 Learnability and the Vapnik-Chervonenkis dimension.J. Assoc. Comput. Mach. 36: 929–965
Borkar V S 1998 Stochastic approximation algorithms: Overview and recent trends.Sadhana 24:
Bush R R, Mosteller F 1958Stochastic models for learning (New York: John Wiley)
Chiang T, Hwang C, Sheu S 1987 Diffusion for global optimisation in Rn.SIAM J. Control Optim. 25: 737–753
Duda R O, Hart P E 1973Pattern classification and scene analysis (New York: Wiley)
Haussler D L 1992 Decision theoretic generalization of the PAC model for neural net and learning applications.Inf. Comput. 100: 78–150
Kashyap R L, Blaydon C C, Fu K S 1970 Stochastic approximation.Adaptive, learning and pattern recognition systems: Theory and applications (eds) J M Mendel, K S Fu (New York: Academic Press)
Kiefer J, Wolfowitz J 1952 Stochastic estimation of a regression function.Ann. Math. Stat. 23: 462–466
Kushner H Y and Yin G G 1997Stochastic approximation algorithms and applications (New York: Springer-Verlag)
Lippmann R P 1987 An introduction to computing with neural nets.IEEE Acoust., Speech Signal Process. Mag. April: 4–22
Minsky M L, Papert S A 1969Perceptrons (Cambridge, MA: MIT Press)
Nagendra G D 1997PAC learning with noisy samples. M E thesis, Dept. of Electrical Engineering, Indian Institute of Science, Bangalore
Narendra K S, Thathachar M A L 1989Learning automata: An introduction (Englewood Cliffs, NJ: Prentice Hall)
Natarajan B K 1991Machine learning: A theoretical approach (San Mateo, CA: Morgan Kaufmann)
Phansalkar V V 1991Learning automata algorithms for connectionist suystems — local and global convergence. Ph D thesis, Dept. of Electrical Engineering, Indian Institute of Science, Bangalore
Rajaraman K, Sastry P S 1996 Finite time analysis of pursuit algorithm for learning automata.IEEE Trans. Syst., Man Cybern. 27: 590–599
Rajaraman K, Sastry P S 1997 A parallel stochastic algorithm for learning logic expressions under noise.J. Indian Inst. Sci. 77: 15–45
Rumelhart D E, Hinton G E, Williams R J 1986 Learning internal representations by error propagation.Parallel distributed processing (eds) D E Rumelhart, J McLlelland (Cambridge, MA: MIT Press) vol. 1
Santharam G 1994Distributed learning with connectionist models for optimisation and control. Ph D thesis, Dept. of Electrical Engineering, Indian Institute of Science, Bangalore
Santharam G, Sastry P S, Thathachar M A L 1994 Continuous action set learning automata for stochastic optimization.J. Franklin Inst. 331: 607–628
Sastry P S, Rajaram K, Ranjan S R 1993 Learning optimal conjunctive concepts using stochastic automata.IEEE Trans. Syst., Man Cybern. 23: 1175–1184
Sastry P S, Phansalkar V V, Thathachar M A L 1994 Decentralised learning of Nash equilibria in multi-person stochastic games with incomplete information.IEEE Trans. Syst., Man Cybern. 24: 769–777
Shapiro I J, Narendera K S 1969 Use of stochastic automata for parameter self optimisation multimodel performance criteria.IEEE Trans. Syst. Sci. Cybern. 5: 352–360
Sklansky J, Wassel G N 1981Pattern classification and trainable machines (New York: Springer-Verlag)
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. 15: 168–175
Thathachar M A L, Sastry P S 1987 Learning optimal discriminant functions through a cooperative game of automata.IEEE Trans. Syst., Man Cybern. 17: 73–85
Thathachar M A L, Sastry P S 1991 Learning automata in stochastic games with incomplete information.Systems and signal processing (eds) R N Madan, N Vishwanathan, R L Kashyap (New Delhi: Oxford and IBH) pp 417–434
Thathachar M A L, Phansalkar V V 1995a Learning the global maximum with parameterised learning automata.IEEE Trans. Neural Networks 6: 398–406
Thathachar M A L, Phansalkar V V 1995b Convergence of teams and hierarchies of learning automata in connectionist systems.IEEE Trans. Syst., Man Cybern. 25: 1459–1469
Thathachar M A L, Arvind M T 1998 Parallel algorithms for modules of learning automata.IEEE Trans. Syst., Man Cybern. B28: 24–33
Vapnik V N 1982Estimation of dependences based on empirical data (New York: Springer-Verlag)
Vapnik V N 1997Nature of statistical learning theory (New York: Springer-Verlag)
Williams R J 1992 Simple statistical gradient-following algorithms for connectionist reinforcement learning.Machine learning 8: 229–256
Author information
Authors and Affiliations
Corresponding authors
Additional information
This work is supported in part by an Indo-US project under ONR grant number N-00014-J-1324.
Rights and permissions
About this article
Cite this article
Sastry, P.S., Thathachar, M.A.L. Learning automata algorithms for pattern classification. Sadhana 24, 261–292 (1999). https://doi.org/10.1007/BF02823144
Issue Date:
DOI: https://doi.org/10.1007/BF02823144