Vapnik-Chervonenkis entropy of the spherical perceptron

Research output: Contribution to journalArticle

4 Scopus citations

Abstract

Perceptron learning of randomly labeled patterns is analyzed using a Gibbs distribution on the set of realizable labelings of the patterns. The entropy of this distribution is an extension of the Vapnik-Chervonenkis (VC) entropy, reducing to it exactly in the limit of infinite temperature. The close relationship between the VC and Gardner entropies can be seen within the replica formalism.

Original languageEnglish (US)
Pages (from-to)3283-3287
Number of pages5
JournalPhysical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics
Volume55
Issue number3
DOIs
StatePublished - Jan 1 1997

All Science Journal Classification (ASJC) codes

  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Condensed Matter Physics

Fingerprint Dive into the research topics of 'Vapnik-Chervonenkis entropy of the spherical perceptron'. Together they form a unique fingerprint.

  • Cite this