1 November 1992 Orthonormalization procedure for optical resonator neural networks
Author Affiliations +
Optical Engineering, 31(11), (1992). doi:10.1117/12.60041
Abstract
The problems arising from nonorthonormality of the stored images in an optical resonator neural network are discussed, and a solution is given whereby the eigenmodes of the resonator can be found. This approach is implemented in computer simulations of the resonator. A number of diverse and distorted input images are successfully identified. Results for individual examples are presented and type I (in-class discrimination) and II (out-of-class discrimination) false alarm rates for this configuration are obtained. We show that by using the information on the convergence rate of an iterative scheme, the performance of the system, as compared to that of a correlation filter, can be improved.
Edwin Ghahramani, L. Roger B. Patterson, "Orthonormalization procedure for optical resonator neural networks," Optical Engineering 31(11), (1 November 1992). http://dx.doi.org/10.1117/12.60041
JOURNAL ARTICLE
12 PAGES


SHARE
KEYWORDS
Holograms

Resonators

Neural networks

Optical resonators

Diffraction

Volume holography

Computer simulations

RELATED CONTENT

The Fast Hartley Transform
Proceedings of SPIE (December 19 1985)

Back to Top