Open Access
December 1996 An overtraining-resistant stochastic modeling method for pattern recognition
E. M. Kleinberg
Ann. Statist. 24(6): 2319-2349 (December 1996). DOI: 10.1214/aos/1032181157

Abstract

We will introduce a generic approach for solving problems in pattern recognition based on the synthesis of accurate multiclass discriminators from large numbers of very inaccurate "weak" models through the use of discrete stochastic processes. Contrary to the standard expectation held for the many statistical and heuristic techniques normally associated with the field, a significant feature of this method of "stochastic modeling" is its resistance to so-called "overtraining." The drop in performance of any stochastic model in going from training to test data remains comparable to that of the component weak models from which it is synthesized; and since these component models are very simple, their performance drop is small, resulting in a stochastic model whose performance drop is also small despite its high level of accuracy.

Citation

Download Citation

E. M. Kleinberg. "An overtraining-resistant stochastic modeling method for pattern recognition." Ann. Statist. 24 (6) 2319 - 2349, December 1996. https://doi.org/10.1214/aos/1032181157

Information

Published: December 1996
First available in Project Euclid: 16 September 2002

zbMATH: 0877.68102
MathSciNet: MR1425956
Digital Object Identifier: 10.1214/aos/1032181157

Subjects:
Primary: 68T05 , 68T10

Keywords: machine learning , pattern recognition

Rights: Copyright © 1996 Institute of Mathematical Statistics

Vol.24 • No. 6 • December 1996
Back to Top