Constructive Incremental Learning From Only Local Information

DMCA

Constructive Incremental Learning From Only Local Information

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Stefan Schaal , Christopher G. Atkeson

Venue:	NEURAL COMPUTATION
Citations:	208 - 40 self

BibTeX

@MISC{Schaal_constructiveincremental,
    author = {Stefan Schaal and Christopher G. Atkeson},
    title = {Constructive Incremental Learning From Only Local Information},
    year = {}
}

OpenURL

Abstract

We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, the size and shape of the receptive field of each locally linear model as well as the parameters of the locally linear model itself are learned independently, i.e., without the need for competition or any other kind of communication. Independent learning is accomplished by incrementally minimizing a weighted local cross validation error. As a result, we obtain a learning system that can allocate resources as needed while dealing with the bias-variance dilemma in a principled way. The spatial localization of the linear models increases robustness towards negative interference. Our learning system can be interpreted as a nonparametric adaptive bandwidth smoother, as a mixture of experts where the experts are trained in isolation, and as a learning system which profits from combining independent expert knowledge on the same problem. This paper illustrates the potential learning capabilities of purely local learning and offers an interesting and powerful approach to learning with receptive fields.

Keyphrases

linear model neural computation constructive incremental learning local information learning system receptive field regression problem bias-variance dilemma incremental learning system powerful approach principled way weighted local cross validation error nonparametric adaptive bandwidth smoother spatial localization independent learning robustness towards negative interference independent expert knowledge local learning model data potential learning capability

DMCA