Constructive Incremental Learning from Only Local Information

DOI Web Site 被引用文献33件
  • Stefan Schaal
    Department of Computer Science, University of Southern California, Los Angeles, CA 90089-2520, U.S.A., and Kawato Dynamic Brain Project (ERATO/JST), 619-02 Kyoto, Japan
  • Christopher G. Atkeson
    College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, U.S.A., and ATR Human Information Processing Laboratories, 619-02 Kyoto, Japan

抄録

<jats:p> 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, that is, 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 toward 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 that profits from combining independent expert knowledge on the same problem. This article illustrates the potential learning capabilities of purely local learning and offers an interesting and powerful approach to learning with receptive fields. </jats:p>

収録刊行物

  • Neural Computation

    Neural Computation 10 (8), 2047-2084, 1998-11-01

    MIT Press - Journals

被引用文献 (33)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ