An adaptive resonance (ART) device has been conceived that is fully optical in the input-output processing path. It is based on holographic information processing in a phase-conjugating crystal. This sets up an associative pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, allowing an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but it does allow learning and makes use of information the other device discards. This device is expected to offer higher information storage density than alternative ART implementations.
D. C. Wunsch et al., "An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation," Proceedings of the RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992, Institute of Electrical and Electronics Engineers (IEEE), Jan 1992.
The definitive version is available at http://dx.doi.org/10.1109/RNNS.1992.268572
RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992
Electrical and Computer Engineering
Keywords and Phrases
Adaptive Optics; Angle-Multiplexed Reference Beams; Associative Pattern Retrieval; Holographic Information Processing; Holographic Storage; Optical Adaptive Resonance Neural Network; Optical Neural Nets; Optical Phase Conjugation; Pattern Classification; Pattern Recognition; Phase Conjugation; Phase-Conjugating Crystal; Reset Mechanism
Article - Conference proceedings
© 1992 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.