Dynamics of on-line gradient descent learning for multilayer neural networks

David Saad, Sara A. Solla

Research output: Contribution to journalArticlepeer-review

Abstract

We consider the problem of on-line gradient descent learning for general two-layer neural networks. An analytic solution is presented and used to investigate the role of the learning rate in controlling the evolution and convergence of the learning process.
Original languageEnglish
Pages (from-to)302-308
Number of pages7
JournalAdvances in Neural Information Processing Systems
Volume8
Publication statusPublished - 1996

Bibliographical note

Copyright of Massachusetts Institute of Technology Press (MIT Press) http://mitpress.mit.edu/mitpress/copyright/default.asp

Keywords

  • on-line
  • gradient descent learning
  • general two-layer neural networks
  • learning rate
  • learning process.

Fingerprint

Dive into the research topics of 'Dynamics of on-line gradient descent learning for multilayer neural networks'. Together they form a unique fingerprint.

Cite this