On-line learning of non-monotonic rules by simple perceptron

Jun Ichi Inoue, Hidetoshi Nishimori, Yoshiyuki Kabashima

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)


We study the generalization ability of a simple perceptron which learns unlearnable rules. The rules are presented by a teacher perceptron with a non-monotonic transfer function. The student is trained in the on-line mode. The asymptotic behaviour of the generalization error is estimated under various conditions. Several learning strategies are proposed and improved to obtain the theoretical lower bound of the generalization error.

Original languageEnglish
Pages (from-to)3795-3816
Number of pages22
JournalJournal of Physics A: Mathematical and General
Issue number11
Publication statusPublished - 1997 Jun 7

ASJC Scopus subject areas

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


Dive into the research topics of 'On-line learning of non-monotonic rules by simple perceptron'. Together they form a unique fingerprint.

Cite this