Abstract

A novel type of a dynamic optical neurochip that uses sensitivity-variable photodiodes (VSPD’s) as variable interconnection weight elements is proposed and analyzed. The chip consists of the line-shaped light-emitting diode array and the VSPD matrix array. A monolithic integration of these arrays is presented. This dynamic chip has advantages such as less optical cross talk, higher processing speed, and realization of analog synaptic weights. Also, experimental results of the VSPD array using metal–semiconductor–metal structure are shown. The results of the computer simulation using this chip as a learning element show that the unwanted effect of the optical cross talk on the recognition rate can be alleviated by the learning capability of the chip. It is also found that the theoretical maximum density is ~2000 neurons/cm² for the backpropagation model.

© 1991 Optical Society of America

Optical learning neurochip with internal analog memory

Yoshikazu Nitta, Jun Ohta, Syuichi Tai, and Kazuo Kyuma
Appl. Opt. 32(8) 1264-1274 (1993)

Variable-sensitivity photodetector that uses a metal–semiconductor–metal structure for optical neural networks

Y. Nitta, J. Ohta, S. Tai, and K. Kyuma
Opt. Lett. 16(8) 611-613 (1991)

Optical neurochip based on a three-layered feed-forward model

J. Ohta, K. Kojima, Y. Nitta, S. Tai, and K. Kyuma
Opt. Lett. 15(23) 1362-1364 (1990)

Optoelectronic associative memory using an advanced optical neurochip

Yoshikazu Nitta, Jun Ohta, Kazumasa Mitsunaga, Syuichi Tai, and Kazuo Kyuma
Appl. Opt. 30(11) 1328-1330 (1991)

Use of a persistent photoconductive array in the learning of an optoelectronic neural processor

Seok Ho Song, Jong-Moon Kim, and Byueng-Su Yoo
Opt. Lett. 16(22) 1771-1773 (1991)