Stochastic backpropagation: A learning algorithm for generalization problems

C. V. Ramamoorthy, Shashi Shekhar

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations

Abstract

Neural networks have traditionally been applied to recognition problems, and most learning algorithms are tailored to those problems. The authors discuss the requirements of learning for generalization, which is NP-complete and cannot be approached by traditional methods based on gradient descent. They present a stochastic learning algorithm based on simulated annealing in weight space. The convergence properties and feasibility of the algorithm are verified.

Original languageEnglish (US)
Pages (from-to)664-671
Number of pages8
JournalProceedings - IEEE Computer Society's International Computer Software & Applications Conference
StatePublished - Dec 1 1989
EventProceedings of the Thirteenth Annual International Computer Software & Applications Conference - COMPSAC 89 - Orlando, FL, USA
Duration: Sep 20 1989Sep 22 1989

Fingerprint Dive into the research topics of 'Stochastic backpropagation: A learning algorithm for generalization problems'. Together they form a unique fingerprint.

Cite this