A Self-Organizing Neural Network For Locus-Addressable Associative Memory

Raghavan, Manoj and Dorai, Chitra (1990) A Self-Organizing Neural Network For Locus-Addressable Associative Memory. In: 1990 International Joint Conference on Neural Networks. IJCNN 1990, 17-21 June, San Diego, CA, Vol.1, 899-904.

Preview

PDF a_self_organising_neural.pdf Download (166kB)

Abstract

A Self-organizing neural network model for locus-Addressable associative memory, and binary pattern recognition is presented. The net may be used for either auto-associative or hetero-associative tasks. Locus - addressability is suggested as a possible mechanism for retrieval of memories without any external cues in the form of partial or corrupted exemplar patterns. The architecture, Which employs competitive dynamics, embodies a parallel search scheme which updates itself adaptively as the learning progresses. A thresholding mechanism ensures the learning of new exemplars. On saturation of the memory capacity, the net thereafter responds to new patterns by recalling exemplars in its memory that are nearest to the presented input in Hamming distance. The stability – Plasticity problem is overcome by ‘fast learning’ and irreversibility of connection-weight changes. This architecture overcomes the orthogonality and linear independence constraints that limit other models.

Item Type:	Conference Paper
Publisher:	IEEE
Additional Information:	Copyright 1990 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	30 May 2006
Last Modified:	19 Sep 2010 04:27
URI:	http://eprints.iisc.ac.in/id/eprint/7062

Actions (login required)

View Item