Unsupervised Learning

DOI Web Site 被引用文献34件
  • H.B. Barlow
    Kenneth Craik Laboratory, Physiological Laboratory, Downing Street, Cambridge, CB2 3EG, England

抄録

<jats:p> What use can the brain make of the massive flow of sensory information that occurs without any associated rewards or punishments? This question is reviewed in the light of connectionist models of unsupervised learning and some older ideas, namely the cognitive maps and working models of Tolman and Craik, and the idea that redundancy is important for understanding perception (Attneave 1954), the physiology of sensory pathways (Barlow 1959), and pattern recognition (Watanabe 1960). It is argued that (1) The redundancy of sensory messages provides the knowledge incorporated in the maps or models. (2) Some of this knowledge can be obtained by observations of mean, variance, and covariance of sensory messages, and perhaps also by a method called “minimum entropy coding.” (3) Such knowledge may be incorporated in a model of “what usually happens” with which incoming messages are automatically compared, enabling unexpected discrepancies to be immediately identified. (4) Knowledge of the sort incorporated into such a filter is a necessary prerequisite of ordinary learning, and a representation whose elements are independent makes it possible to form associations with logical functions of the elements, not just with the elements themselves. </jats:p>

収録刊行物

被引用文献 (34)*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