Abstract

We study certain neural network architectures, which admit to optical implementations, from the point of view of projection methods. This approach enables us to uncover some interesting facts about the stable states of such networks. For example, a Hopfield-type associative content-addressable memory (ACAM) using a hard-limiter nonlinearity has three kinds of possible stable states. If the hard-limiter is replaced by a unity-slope saturation nonlinearity, there are only two kinds of stable states. These and other results demonstrate the utility of using projection methods in analyzing the dynamic behavior of neural networks.

© 1990 Optical Society of America

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)

Class of continuous level associative memory neural nets

Robert J. Marks
Appl. Opt. 26(10) 2005-2010 (1987)

Neural network model using interpattern association

Taiwei Lu, Xin Xu, Sudong Wu, and Francis T. S. Yu
Appl. Opt. 29(2) 284-288 (1990)

Optical neural network with bipolar neural states

Xu-Ming Wang and Guo-Guang Mu
Appl. Opt. 31(23) 4712-4719 (1992)

Optical associative memory model based on neural networks having variable interconnection weights

Bohdan Macukow and Henri H. Arsenault
Appl. Opt. 26(5) 924-928 (1987)