On the characteristics of the autoassociative memory with nonzero-diagonal terms in the memory matrix

Authors:
Jung-Hua Wang;Thomas F. Krile;John F. Walkup;Tai-Lang Jong
Affiliations:
Department of Electrical Engineering, Texas Tech University, Lubbock, TX 79409-3102 USA;Department of Electrical Engineering, Texas Tech University, Lubbock, TX 79409-3102 USA;Department of Electrical Engineering, Texas Tech University, Lubbock, TX 79409-3102 USA;Department of Electrical Engineering, National Tsing-Hua University, Taiwan
Venue:
Neural Computation
Year:
1991

Citing 5
Cited 1

A Quantitative Comparison of the Performance of Three Discrete Distributed Associative Memory Models

IEEE Transactions on Computers
Basins of attraction of neural network models

AIP Conference Proceedings 151 on Neural Networks for Computing
The capacity of the Hopfield associative memory

IEEE Transactions on Information Theory
Part segmentation for object recognition

Neural Computation
Determination of Hopfield associative memory characteristics using a simple parameter

Neural Networks

Original Contribution: Strongly diluted networks with selfinteraction

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A statistical method is applied to explore the unique characteristics of a certain class of neural network autoassociative memory with N neurons and first-order synaptic interconnections. The memory matrix is constructed to store M = N vectors based on the outer-product learning algorithm. We theoretically prove that, by setting all the diagonal terms of the memory matrix to be M and letting the input error ratio = 0, the probability of successful recall Pr steadily decreases as increases, but as increases past 1.0, Pr begins to increase slowly. When 0 Pr 0.99, the tradeoff between the number of stable states and their attraction force is analyzed and the memory capacity is shown to be 0.15N at best.