Performance analysis of associative memories with nonlinearities in the correlation domain

Abstract

A matched filter-based architecture for associative memories (MFAMs) has been proposed by many researchers. The correlation from a leg of a matched filter bank, after being altered nonlinearly, weights its corresponding library vector. The weighted vectors are summed and clipped to give an estimate of the library vector closest to the input. We analyze the performance of such architectures for binary and/or bipolar inputs and libraries. Sufficient conditions are derived for the correlation nonlinearity so that the MFAM outputs the correct result. If, for example, N bipolar library vectors are stored, the correlation nonlinearity Z(x) = N^x/2 will always result in that library vector closest to the input in the Hamming sense.

© 1988 Optical Society of America

Holographic associative memory with nonlinearities in the correlation domain

Y. Owechko, G. J. Dunning, E. Marom, and B. H. Soffer
Appl. Opt. 26(10) 1900-1910 (1987)

Properties of holographic associative memory prepared by the polarization encoding process

Seok Ho Song and Sang Soo Lee
Appl. Opt. 27(15) 3149-3154 (1988)

Nearly optimal correlations for shift-invariant associative memories

Jehad Khoury, Peter D. Gianino, and Charles L. Woods
Appl. Opt. 34(20) 3971-3980 (1995)

Optical implementation of associative memory with controlled nonlinearity in the correlation domain

Ravindra A. Athale, Harold H. Szu, and Carl B. Friedlander
Opt. Lett. 11(7) 482-484 (1986)

Hopfield model associative memory with nonzero-diagonal terms in memory matrix

Gene R. Gindi, Arthur F. Gmitro, and K. Parthasarathy
Appl. Opt. 27(1) 129-134 (1988)