A BIOLOGICALLY-INSPIRED IMPROVED MAXNET

Authors
YADIDPECHT O GUR M
Citation
O. Yadidpecht et M. Gur, A BIOLOGICALLY-INSPIRED IMPROVED MAXNET, IEEE transactions on neural networks, 6(3), 1995, pp. 757-759
Citations number
8
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
6
Issue
3
Year of publication
1995
Pages
757 - 759
Database
ISI
SICI code
1045-9227(1995)6:3<757:ABIM>2.0.ZU;2-M
Abstract
A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new n et are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementat ion for the modified net is presented.