Photorefractive Adaptive Resonance Neural Network
This paper describes a new optical processing devices that can handle large patterns and can accommodate a large template. The design, layout of the system which uses holographic information processing in photorefractive crystals is given. The operating principle for pattern classification is explained. It is proposed that it can be applied to high-resolution image processing which requires large input fields, where its high storage density gives a distinct performance edge over other schemes that cannot process the large number of pixels.
D. C. Wunsch et al., "Photorefractive Adaptive Resonance Neural Network," Applied Optics, vol. 32, no. 8, pp. 1399-1407, Optical Society of America, Jan 1993.
The definitive version is available at http://dx.doi.org/10.1364/AO.32.001399
Electrical and Computer Engineering
International Standard Serial Number (ISSN)
Article - Journal
© 1993 Optical Society of America, All rights reserved.