Abstract
Pattern recognition essentially deals with the training and classification of patterns, where the distribution of the features is assumed unknown. However, in almost all the reported results, a fundamental assumption made is that this distribution, although unknown, is stationary. In this paper, we shall relax this assumption and assume that the class-conditional distribution is non-stationary. To now render the training and classification feasible, we present a novel estimation strategy, involving the so-called Stochastic Learning Weak Estimator (SLWE). The latter, whose convergence is weak, is used to estimate the parameters of a binomial distribution using the principles of stochastic learning. Even though our method includes a learning coefficient, λ, it turns out that the mean of the final estimate is independent of λ , the variance of the final distribution decreases with λ , and the speed decreases with λ . Similar results are true for the multinomial case. To demonstrate the power of these estimates in data which is truly “non-stationary”, we have used them in two pattern recognition exercises, the first of which involves artificial data, and the second which involves the recognition of the types of data that are present in news reports of the Canadian Broadcasting Corporation (CBC). The superiority of the SLWE in both these cases is demonstrated.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bickel, P., Doksum, K.: Mathematical Statistics: Basic Ideas and Selected Topics, 2nd edn., vol. I. Prentice Hall, Englewood Cliffs (2000)
Blake, C., Merz, C.: UCI repository of machine learning databases (1998)
Casella, G., Berger, R.: Statistical Inference, 2nd edn. Brooks/Cole Pub. Co., Pacific Grove (2001)
Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. John Wiley and Sons, Inc., New York (2000)
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, London (1990)
Herbrich, R.: Learning Kernel Classifiers: Theory and Algorithms. MIT Press, Cambridge (2001)
Jang, Y.M.: Estimation and Prediction-Based Connection Admission Control in Broadband Satellite Systems. ETRI Journal 22(4), 40–50 (2000)
Jones, B., Garthwaite, P., Jolliffe, I.: Statistical Inference, 2nd edn. Oxford University Press, Oxford (2002)
Kushner, H., Yin, G.: Stochastic Approximation and Recursive Algorithms and Applications, 2nd edn. Springer, Heidelberg (2003)
Lakshmivarahan, S.: Learning Algorithms Theory and Applications. Springer, New York (1981)
Lakshmivarahan, S., Thathachar, M.A.L.: Absolutely Expedient Algorithms for Stochastic Automata. IEEE Trans. on System, Man and Cybernetics SMC-3, 281–286 (1973)
Lanctôt, J.K., Oommen, B.J.: Discretized Estimator Learning Automata. IEEE Trans. on Systems, Man and Cybernetics 22(6), 1473–1483 (1992)
Narendra, K., Thathachar, M.: Learning Automata. An Introduction. Prentice-Hall, Englewood Cliffs (1989)
Norris, J.: Markov Chains. Springer, Heidelberg (1999)
Oommen, B.J., Rueda, L.: Stochastic Learning-based Weak Estimation of Multinomial Random Variables and Its Applications to Non-stationary Environments (2004) (submitted for publication)
Oommen, B.J.: Absorbing and Ergodic Discretized Two-Action Learning Automata. IEEE Trans. on System, Man and Cybernetics SMC-16, 282–296 (1986)
Oommen, B.J., Agache, M.: Continuous and Discretized Pursuit Learning Schemes: Various Algorithms and Their Comparison. IEEE Trans. on Systems, Man and Cybernetics SMC-31(B), 277–287 (2001)
Oommen, B.J., Christensen, J.R.P.: Epsilon-Optimal Discretized Reward-Penalty Learning Automata. IEEE Trans. on System, Man and Cybernetics SMC-18, 451–458 (1988)
Oommen, B.J., Lanctôt, J.K.: Discretized Pursuit Learning Automata. IEEE Trans. on System, Man and Cybernetics 20(4), 931–938 (1990)
Oommen, B.J., Rueda, L.: A New Family of Weak Estimators for Training in Non-stationary Distributions. In: Proceedings of the Joint IAPR International Workshops SSPR 2004 and SPR 2004, Lisbon, Portugal, pp. 644–652 (2004)
Papadimitriou, G.I.: A New Approach to the Design of Reinforcement Schemes for Learning Automata: Stochastic Estimator Learning Algorithms. IEEE Trans. on Knowledge and Data Engineering 6, 649–654 (1994)
Papadimitriou, G.I.: Hierarchical Discretized Pursuit Nonlinear Learning Automata with Rapid Convergence and High Accuracy. IEEE Trans. on Knowledge and Data Engineering 6, 654–659 (1994)
Rajaraman, K., Sastry, P.S.: Finite Time Analysis of the Pursuit Algorithm for Learning Automata. IEEE Trans. on Systems, Man and Cybernetics 26(4), 590–598 (1996)
Ross, S.: Introduction to Probability Models, 2nd edn. Academic Press, London (2002)
De Santo, M., Percannella, G., Sansone, C., Vento, M.: A multi-expert approach for shot classification in news videos. In: Campilho, A.C., Kamel, M.S. (eds.) ICIAR 2004. LNCS, vol. 3211, pp. 564–571. Springer, Heidelberg (2004)
Shao, J.: Mathematical Statistics, 2nd edn. Springer, Heidelberg (2003)
Sprinthall, R.: Basic Statistical Analysis, 2nd edn. Allyn and Bacon (2002)
Thathachar, M.A.L., Oommen, B.J.: Discretized Reward-Inaction Learning Automata. Journal of Cybernetics and Information Sceinces, 24–29 (spring 1979)
Thathachar, M.A.L., Sastry, P.S.: A Class of Rapidly Converging Algorithms for Learning Automata. IEEE Trans. on Systems, Man and Cybernetics SMC-15, 168–175 (1985)
Thathachar, M.A.L., Sastry, P.S.: Estimator Algorithms for Learning Automata. In: Proc. of the Platinum Jubilee Conference on Systems and Signal Processing, Bangalore, India (December 1986)
Watkins, C.: Learning from Delayed Rewards. PhD thesis. University of Cambridge, England (1989)
Webb, A.: Statistical Pattern Recognition, 2nd edn. John Wiley & Sons, N.York (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oommen, B.J., Rueda, L. (2005). On Utilizing Stochastic Learning Weak Estimators for Training and Classification of Patterns with Non-stationary Distributions. In: Furbach, U. (eds) KI 2005: Advances in Artificial Intelligence. KI 2005. Lecture Notes in Computer Science(), vol 3698. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11551263_10
Download citation
DOI: https://doi.org/10.1007/11551263_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28761-2
Online ISBN: 978-3-540-31818-7
eBook Packages: Computer ScienceComputer Science (R0)