Share Email Print

Optical Engineering

Novel two-layer neural multiassociative memory model
Author(s): Abdul Aziz Bhatti; Nalin Zhou
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A novel, two-layer VLSI realizable, modular and expandable neural network multiassociative memory model is proposed. When compared to the Hopfield model, it requires 0(N) connections for N-bit long vectors; yields improved error correction and storage capabilities and a faster convergence rate, avoids the storage of false memories, and possesses analogies to biological neural networks.

Paper Details

Date Published: 1 October 1992
PDF: 5 pages
Opt. Eng. 31(10) doi: 10.1117/12.59883
Published in: Optical Engineering Volume 31, Issue 10
Show Author Affiliations
Abdul Aziz Bhatti, Advanced Computers and Technology (United States)
Nalin Zhou, Advanced Computers and Technology (United States)

© SPIE. Terms of Use
Back to Top