On the generalization ability of diluted perceptrons

P. Kuhlmann, K. R. Muller

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

A linearly separable Boolean function is teamed by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.

Original languageEnglish
Article number026
Pages (from-to)3759-3774
Number of pages16
JournalJournal of Physics A: Mathematical and General
Volume27
Issue number11
DOIs
Publication statusPublished - 1994

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Mathematical Physics
  • Physics and Astronomy(all)

Fingerprint

Dive into the research topics of 'On the generalization ability of diluted perceptrons'. Together they form a unique fingerprint.

Cite this