Title :
An optical adaptive resonance neural network utilizing phase conjugation
Author :
Wunsch, Donald C., II ; Morris, D.J. ; Caudell, Thomas P. ; Falk, R. Aaron
Author_Institution :
Boeing Co., Seattle, WA, USA
Abstract :
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
Keywords :
adaptive optics; holographic storage; optical neural nets; optical phase conjugation; pattern recognition; angle-multiplexed reference beams; associative pattern retrieval; holographic information processing; optical adaptive resonance neural network; pattern classification; phase conjugation; phase-conjugating crystal; reset mechanism; Adaptive optics; Adaptive systems; Holographic optical components; Holography; Neural networks; Optical computing; Optical devices; Optical fiber networks; Resonance; Subspace constraints;
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
DOI :
10.1109/RNNS.1992.268572