Abstract

A shift-invariant neural network that uses the translation-invariant property of the modulus Fourier spectra with the heteroassociation interpattern association memory is proposed. A binary encoding of a spectral sampling of the training set is used to preserve the main features. Computer simulations and experimental demonstrations are provided that show the shift-invariant property of the proposed optical neural network.

© 1994 Optical Society of America

Neural network model using interpattern association

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

Unipolar interpattern association neural networks

Chii-Maw Uang, Guowen Lu, and Francis T. S. Yu
Opt. Lett. 19(1) 52-54 (1994)

Redundant-interconnection interpattern-association neural network

Xiangyang Yang, Taiwei Lu, Francis T. S. Yu, and Don A. Gregory
Appl. Opt. 30(35) 5182-5187 (1991)

Gray-level discrete associative memory

Francis T. S. Yu, Chii-Maw Uang, and Shizhuo Yin
Appl. Opt. 32(8) 1322-1329 (1993)

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

Chwan-Hwa Wu and Hua-Kuang Liu
Appl. Opt. 33(11) 2210-2217 (1994)