Unipolar terminal-attractor-based neural associative memory with adaptive threshold and perfect convergence

Abstract

A perfectly convergent unipolar neural associative-memory system based on nonlinear dynamical terminal attractors is presented. With adaptive setting of the threshold values for the dynamic iteration for the unipolar binary neuron states with terminal attractors, perfect convergence is achieved. This achievement and correct retrieval are demonstrated by computer simulation. The simulations are completed (1) by exhaustive tests with all of the possible combinations of stored and test vectors in small-scale networks and (2) by Monte Carlo simulations with randomly generated stored and test vectors in large-scale networks with an M/N ratio of 4 (M is the number of stored vectors; N is the number of neurons < 256). An experiment with exclusive-oR logic operations with liquid-crystal-television spatial light modulators is used to show the feasibility of an optoelectronic implementation of the model. The behavior of terminal attractors in basins of energy space is illustrated by examples.

Additional Information

© 1994 Optical Society of America. Received 1 October 1992; revised manuscript received 24 August 1993. This paper describes research that was jointly sponsored by the Advanced Research Projects Agency and the Information Systems Branch, Office of Space Science Applications, NASA, and was performed by the Center for Space Microelectronics Technology, Jet Propulsion Laboratory, California Institute of Technology, under a contract with NASA. C. Wu was supported by the Center of the Commercial Development for Space Power and Advanced Electronics/NASA. We thank Joseph Diep for his experimental assistance, Annie Aroyan for typing the manuscript, and Elizabeth A. Johnson, Margaret Hartley, and Regina Dragoin for editing this manuscript.

Attached Files

Published - WUCao94.pdf

Files

Additional details