Effect of time correlation of input patterns on the convergence of on-line learning

Tsuyoshi Hondou, Mitsuaki Yamamoto, Yasuji Sawada, Yoshihiro Hayakawa

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

We studied the effects of time correlation of subsequent patterns on the convergence of on-line learning by a feedforward neural network with the backpropagation algorithm. By using a chaotic time series as sequences of correlated patterns, we found that the unexpected scaling of converging time with the learning parameter emerges when time-correlated patterns accelerate the learning process.

Original languageEnglish
Pages (from-to)4217-4220
Number of pages4
JournalPhysical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics
Volume53
Issue number4
DOIs
Publication statusPublished - 1996

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Effect of time correlation of input patterns on the convergence of on-line learning'. Together they form a unique fingerprint.

Cite this