Adaptive-clustering optical neural net
- 10 June 1990
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 29 (17), 2603-2615
- https://doi.org/10.1364/ao.29.002603
Abstract
Pattern recognition techniques (for clustering and linear discriminant function selection) are combined with neural net methods (that provide an automated method to combine linear discriminant functions into piecewise linear discriminant surfaces). The resulting adaptive-clustering neural net is suitable for optical implementation and has certain desirable properties in comparison with other neural nets. Simulation results are provided.Keywords
This publication has 17 references indexed in Scilit:
- On hidden nodes for neural netsIEEE Transactions on Circuits and Systems, 1989
- All-optical error-signal generation for backpropagation learning in optical multilayer neural networksOptics Letters, 1989
- Continuous-time optical neural network associative memoryOptics Letters, 1989
- Bidirectional associative memoriesIEEE Transactions on Systems, Man, and Cybernetics, 1988
- Multilayer optical learning networksApplied Optics, 1987
- Optical implementations of associative networks with versatile adaptive learning capabilitiesApplied Optics, 1987
- Dynamic optical interconnects: volume holograms as optical two-port operatorsApplied Optics, 1987
- Evaluation of the use of the Hopfield neural network model as a nearest-neighbor algorithmApplied Optics, 1986
- Associative holographic memory with feedback using phase-conjugate mirrorsOptics Letters, 1986
- Optical information processing based on an associative-memory model of neural nets with thresholding and feedbackOptics Letters, 1985