Holographic On-Line Learning Machine for Multicategory Classification
- 1 July 1990
- journal article
- Published by IOP Publishing in Japanese Journal of Applied Physics
- Vol. 29 (7A), L1332
- https://doi.org/10.1143/jjap.29.l1332
Abstract
A holographic on-line learning machine that is capable of multicategory classification is described. The system exactly implements the single-layer perceptron algorithm in a fully parallel and analog fashion. The performance of the adaptive network is successfully tested for up to 24 characters with different scale and rotation. Also, a compact and robust version of the holographic learning machine is proposed.Keywords
This publication has 12 references indexed in Scilit:
- Holographic implementation of a learning machine based on a multicategory perceptron algorithmOptics Letters, 1989
- Motivations for using ferroelectric liquid crystal spatial light modulators in neurocomputingApplied Optics, 1989
- Experimental learning in an optical perceptronlike neural networkOptics Letters, 1989
- Optical associatron: a simple model for optical associative memoryApplied Optics, 1989
- Higher order associative memories and their optical implementationsNeural Networks, 1988
- Adaptive optical networks using photorefractive crystalsApplied Optics, 1988
- Multilayer optical learning networksApplied Optics, 1987
- Optical implementations of associative networks with versatile adaptive learning capabilitiesApplied Optics, 1987
- Electrical Control in Photoferroelectric Materials for Optical StorageApplied Optics, 1974
- Improved Electrooptic Materials and Fixing Techniques for Holographic RecordingApplied Optics, 1972