On utilizing stochastic learning weak estimators for training and classification of patterns with non-stationary distributions

Authors:
B. John Oommen;Luis Rueda
Affiliations:
School of Computer Science, Carleton University, Ottawa, ON, Canada;School of Computer Science, University of Windsor, Windsor, ON, Canada
Venue:
KI'05 Proceedings of the 28th annual German conference on Advances in Artificial Intelligence
Year:
2005

Citing 13
Cited 0

Absorbing and ergodic discretized two-action learning automata

IEEE Transactions on Systems, Man and Cybernetics
Learning automata: an introduction

Learning automata: an introduction
Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
Statistical inference

Statistical inference
AI Game Programming Wisdom

AI Game Programming Wisdom
Learning Algorithms Theory and Applications

Learning Algorithms Theory and Applications
A New Approach to the Design of Reinforcement Schemes for Learning Automata: Stochastic Estimator Learning Algorithms

IEEE Transactions on Knowledge and Data Engineering
Hierarchical Discretized Pursuit Nonlinear Learning Automata with Rapid Convergence and High Accuracy

IEEE Transactions on Knowledge and Data Engineering
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Introduction to Probability Models, Ninth Edition

Introduction to Probability Models, Ninth Edition
Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments

Pattern Recognition
Finite time analysis of the pursuit algorithm for learning automata

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Continuous and discretized pursuit learning schemes: variousalgorithms and their comparison

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

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.