Abstract

An optical neural network using two tightly cascaded liquid crystal televisions is presented. This new optical architecture offers compactness in size, ease of alignment, higher light efficiency, better image quality, and low cost. The implementation of the autoassociative and heteroassociative memories is given.

© 1990 Optical Society of America

Optical neural network with pocket-sized liquid-crystal televisions

Francis T. S. Yu, Taiwei Lu, Xiangyang Yang, and Don A. Gregory
Opt. Lett. 15(15) 863-865 (1990)

Optical disk based neural network

Taiwei Lu, Kyusun Choi, Shudong Wu, Xin Xu, and Francis T. S. Yu
Appl. Opt. 28(22) 4722-4724 (1989)

Two-dimensional programmable optical neural network

Taiwei Lu, Shudong Wu, Xin Xu, and Francis T. S. Yu
Appl. Opt. 28(22) 4908-4913 (1989)

Neural network model using interpattern association

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

Implementation of a large-scale optical neural network by use of a coaxial lenslet array for interconnection

Shengquan Gao, Jianwen Yang, Zhanbing Feng, and Yanxin Zhang
Appl. Opt. 36(20) 4779-4783 (1997)