Abstract

Two optical implementations of production systems are advanced. The production systems operate on a knowledge base where facts and rules are encoded as formulas in propositional calculus. The first implementation is a binary neural network. An analog neural network is used to include reasoning with uncertainties. The second implementation uses a new optical symbolic substitution correlator. This implementation is useful when a set of similar situations has to be handled in parallel on one processor.

© 1988 Optical Society of America

Architectural relationships involving symbolic substitution

John L. Johnson
Appl. Opt. 27(3) 529-533 (1988)

Optical symbolic substitution: system design using phase-only holograms

Joseph N. Mait and Karl-Heinz Brenner
Appl. Opt. 27(9) 1692-1700 (1988)

Optical correlator production system neural net

David Casasent and Elizabeth Botha
Appl. Opt. 31(8) 1030-1040 (1992)

Digital optical processor based on symbolic substitution using holographic matched filtering

Ho-In Jeon, Mustafa A. G. Abushagur, Alexander A. Sawchuk, and B. Keith Jenkins
Appl. Opt. 29(14) 2113-2125 (1990)

Optical symbolic substitution for morphological transformations

David Casasent and Elizabeth Botha
Appl. Opt. 27(18) 3806-3810 (1988)