On the Effect of Noise on the Moore-Penrose Generalized Inverse Associative Memory

Authors:
G. S. Stiles;Dong-Lih Denq
Affiliations:
Department of Electrical Engineering, Utah State University, Logan, UT 84322/ Department of Electrical and Computer Engineering, Syracuse University, Syracuse, NY 13210.;Department of Electrical Engineering, Utah State University, Logan, UT 84322.
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1985

Citing 0
Cited 4

Distributed and Fault-Tolerant Computation for Retrieval Tasks Using Distributed Associative Memories

IEEE Transactions on Computers - Fault-Tolerant Computing
Original Contribution: Further noise rejection in linear associative memories

Neural Networks
Original Contribution: High capacity pattern recognition associative processors

Neural Networks
Improving the classification performance of optimal linear associative memory in the presence of outliers

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I

Quantified Score

Hi-index	0.14

Visualization

Abstract

Monte Carlo simulations of the continuous Moore-Penrose generalized inverse associative memory (Kohonen [l]) have shown that the noise-to-signal ratio is improved on recall in the autoassociative case as long as the number of vector pairs stored is less than the number of components per vector. In the heteroassociative case, however, the noise-to-signal ratio may actually be greatly increased upon recall, particularly as the number of vector pairs stored approaches the number of components per vector. The increase in output noise-to-signal ratio in the heteroassociative case is found to be due to the fact that the inverse of the product of the key vector matrix with its transpose may increase without bound in spite of the fact that the key vectors are linearly independent.