Abstract

Optical-processor architectures for various forms of the alternating-projection neural network are considered. Required iteration is performed by passive optical feedback. No electronics or slow optics (e.g., phase conjugators) are used in the feedback path. The processor can be taught a new training vector by viewing it only once. If the desired outputs are trained to be either ±1, then the network can be configured to converge in one iteration.

© 1988 Optical Society of America

Four-quadrant optical matrix–vector multiplication machine as a neural-network processor

S. Abramson, D. Saad, E. Marom, and N. Konforti
Appl. Opt. 32(8) 1330-1337 (1993)

Optical processor for a binarized neural network

Long Huang and Jianping Yao
Opt. Lett. 47(15) 3892-3895 (2022)

Coaxial architecture of an optical neural network with a lenslet array

Shengquan Gao, Yanxin Zhang, Jianwen Yang, and Guoguang Mu
Opt. Lett. 19(24) 2155-2157 (1994)

Optical cellular processor architecture. 1 : Principles

Jean Taboury, J. M. Wang, Pierre Chavel, F. Devos, and Patrick Garda
Appl. Opt. 27(9) 1643-1650 (1988)

Optical production systems using neural networks and symbolic substitution

Elizabeth Botha, David Casasent, and Etienne Barnard
Appl. Opt. 27(24) 5185-5193 (1988)