Optimal performance of a feed-forward network at statistical discrimination tasks

W. Bialek, R. Scalettar, A. Zee

Research output: Contribution to journalArticle

2 Scopus citations

Abstract

Within the context of a particular statistical discrimination task, we make a quantitative comparison between the performance of a feed-forward neural network and the information-theoretic optimal performance. We also address the ability of such networks to generalize and the effect of network architecture on performance.

Original languageEnglish (US)
Pages (from-to)141-156
Number of pages16
JournalJournal of Statistical Physics
Volume57
Issue number1-2
DOIs
StatePublished - Oct 1 1989
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Statistical and Nonlinear Physics
  • Mathematical Physics

Keywords

  • Neural network
  • information theory
  • optimal performance
  • statistical discrimination
  • visual system

Fingerprint Dive into the research topics of 'Optimal performance of a feed-forward network at statistical discrimination tasks'. Together they form a unique fingerprint.

  • Cite this