Optical implementations of radial basis classifiers

10 March 1993

journal article
Published by Optica Publishing Group in Applied Optics

Vol. 32 (8) , 1370-1379
https://doi.org/10.1364/ao.32.001370

Abstract

We describe two optical systems based on the radial basis function approach to pattern classification. An optical-disk-based system for handwritten character recognition is demonstrated. The optical system computes the Euclidean distance between an unknown input and 650 stored patterns at a demonstrated rate of 26,000 pattern comparisons/s. The ultimate performance of this system is limited by optical-disk resolution to 1011 binary operations/s. An adaptive system is also presented that facilitates on-line learning and provides additional robustness.

Keywords

This publication has 8 references indexed in Scilit:

Silicon VLSI/ferroelectric liquid crystal technology for micropower optoelectronic computing devices
Applied Optics, 1990
Networks for approximation and learning
Proceedings of the IEEE, 1990
Optical memory disks in optical information processing
Applied Optics, 1990
Joint transform correlator using an amorphous silicon ferroelectric liquid crystal spatial light modulator
Optics Communications, 1990
Fast Learning in Networks of Locally-Tuned Processing Units
Neural Computation, 1989
Image correlators using optical memory disks
Optics Letters, 1989
Adaptive optical networks using photorefractive crystals
Applied Optics, 1988
Nearest neighbor pattern classification
IEEE Transactions on Information Theory, 1967