Electronic Implementation of Associative Memory Based on Neural Network Models

An electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on systems, man, and cybernetics man, and cybernetics, 1987-03, Vol.17 (2), p.325-331
Main Authors: Moopenn, A., Lambe, John, Thakoor, A. P.
Format: Article
Language:English
Subjects:
Applied sciences
Associative memory
Automatic control
Computer Systems
Couplings
Electronics
Exact sciences and technology
Kinematics
Laboratories
Manipulator dynamics
Neural networks
Robotics and automation
Service robots
Springs
Storage and reproduction of information
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with the help of asymmetrical extra connections are discussed. The stability of the matrix memory system incorporating a unique local inhibition scheme is analyzed in terms of local minimization of an energy function. The memory's stability, dynamic behavior, and recall capability are investigated using a 32-"neuron" electronic neural network memory with a 1024-programmable binary connection matrix.
ISSN:0018-9472
2168-2909
DOI:10.1109/TSMC.1987.4309044