Stacked generalization

DMCA

Stacked generalization (1992)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by David H. Wolpert

Venue:	NEURAL NETWORKS
Citations:	731 - 9 self

BibTeX

@ARTICLE{Wolpert92stackedgeneralization,
    author = {David H. Wolpert},
    title = {Stacked generalization},
    journal = {NEURAL NETWORKS},
    year = {1992},
    volume = {5},
    pages = {241--259}
}

OpenURL

Abstract

This paper introduces stacked generalization, a scheme for minimizing the generalization error rate of one or more generalizers. Stacked generalization works by deducing the biases of the generalizer(s) with respect to a provided learning set. This deduction proceeds by generalizing in a second space whose inputs are (for example) the guesses of the original generalizers when taught with part of the learning set and trying to guess the rest of it, and whose output is (for example) the correct guess. When used with multiple generalizers, stacked generalization can be seen as a more sophisticated version of cross-validation, exploiting a strategy more sophisticated than cross-validation’s crude winner-takes-all for combining the individual generalizers. When used with a single generalizer, stacked generalization is a scheme for estimating (and then correcting for) the error of a generalizer which has been trained on a particular learning set and then asked a particular question. After introducing stacked generalization and justifying its use, this paper presents two numerical experiments. The first demonstrates how stacked generalization improves upon a set of sepa-rate generalizers for the NETtalk task of translating text to phonemes. The second demonstrates how stacked generalization improves the performance of a single surface-fitter. With the other experimental evidence in the literature, the usual arguments supporting cross-validation, and the abstract justifications presented in this paper, the conclusion is that for almost any real-world generalization problem one should use some version of stacked generalization to minimize the generalization error rate. This paper ends by discussing some of the variations of stacked generalization, and how it touches on other fields like chaos theory.

Keyphrases

stacked generalization generalization error rate sepa-rate generalizers learning set ab-stract justification sophisticated version generalization work cross-vali-dation crude winner-takes-all particular ques-tion chaos theory particular learning set numer-ical experiment single generalizer deduction proceeds ex-perimental evidence individual generalizers error estimation single surface-fitter general-ization error rate nettalk task real-world gener-alization problem second space usual argument multiple generalizers correct guess original generalizers key word

DMCA