Neifeld, Mark A. and Psaltis, Demetri (1993) Optical implementations of radial basis classifiers. Applied Optics, 32 (8). pp. 1370-1379. ISSN 0003-6935 http://resolver.caltech.edu/CaltechAUTHORS:NEIao93b
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:NEIao93b
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 10^11 binary operations/s. An adaptive system is also presented that facilitates on-line learning and provides additional robustness.
|Additional Information:||© Copyright 1993 Optical Society of America. Received 21 May 1992. This work was supported by the U.S. Army Research Office and the Defense Advanced Research Projects Agency. The authors thank Seiji Kobayashi of the Sony Corporation, Subrata Rakshit, and Alan Yamamura for assistance with the optical-disk recording system.|
|Subject Keywords:||Neural networks, radial basis functions, pattern recognition, optical disk|
|Official Citation:||M. A. Neifeld and D. Psaltis, "Optical implementations of radial basis classifiers," Appl. Opt. 32, 1370- (1993) http://www.opticsinfobase.org/abstract.cfm?URI=ao-32-8-1370|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Archive Administrator|
|Deposited On:||22 Jun 2008|
|Last Modified:||26 Dec 2012 10:07|
Repository Staff Only: item control page