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

Author

Wu, Chwan-Hwa John ; Liu, Hua-Kuang

Author_Institution

Dept. of Electr. Eng., Auburn Univ., AL, USA

Volume

1

fYear

1992

fDate

7-11 Jun 1992

Firstpage

47

Abstract

A unipolar terminal-attractor-based neural associative memory (TABAM) system with adaptive threshold and perfect convergence is presented. By adaptively setting the threshold values for the dynamic iteration for the unipolar binary neuron states with terminal attractors and an inner-product approach, it is demonstrated by means of computer simulation that perfect convergence and correct retrieval can be achieved. The simulation is completed with a small number of stored states (M) and a small number of neurons (N) but a large M/N ratio. An experiment with exclusive-OR logic operation using LCTV (liquid-crystal TV) SLM (spatial light modulators) is used to show the feasibility of the optoelectronic implementation of the models

Keywords

content-addressable storage; convergence; liquid crystal devices; optical neural nets; optical storage; spatial light modulators; LCTV; SLM; adaptive threshold; dynamic iteration; exclusive-OR logic operation; inner-product; neural associative memory; optoelectronic implementation; perfect convergence; unipolar binary neuron states; unipolar terminal-attractor-based; Associative memory; Convergence; Hopfield neural networks; Neural networks; Neurons; Nonlinear optics; Optical crosstalk; Optical modulation; Propulsion; Space technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.287214

Filename

287214