Modified MAXNET with fast convergence net

Orly Yadid-Pecht, Moshe Gur

Research output: Contribution to journalConference articlepeer-review

Abstract

A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.

Original languageEnglish
Pages (from-to)111-118
Number of pages8
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume2243
DOIs
StatePublished - 2 Mar 1994
Externally publishedYes
EventApplications of Artificial Neural Networks V 1994 - Orlando, United States
Duration: 4 Apr 19948 Apr 1994

Fingerprint

Dive into the research topics of 'Modified MAXNET with fast convergence net'. Together they form a unique fingerprint.

Cite this