3 May 1988 Architectures For A Continuous Level Neural Network Based On Alternating Orthogonal Projections
Author Affiliations +
Proceedings Volume 0882, Neural Network Models for Optical Computing; (1988) https://doi.org/10.1117/12.944105
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
Abstract
Optical processor architectures for various forms of the alternating projection neural network (APNN) are considered. Required iteration is performed by passive optical feedback using only free space and guided propagation. No electronics or slow optics (e.g. phase conjugators) are used. The processor can be taught a new training vector by viewing it only once.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Robert J Marks, Robert J Marks, Les E Atlas, Les E Atlas, Seho Oh, Seho Oh, Kwan F Cheung, Kwan F Cheung, } "Architectures For A Continuous Level Neural Network Based On Alternating Orthogonal Projections", Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); doi: 10.1117/12.944105; https://doi.org/10.1117/12.944105
PROCEEDINGS
3 PAGES


SHARE
Back to Top