Optical implementation of a second-order neural network
- 1 January 1991
- journal article
- Published by Optica Publishing Group in Optics Letters
- Vol. 16 (1) , 45-47
- https://doi.org/10.1364/ol.16.000045
Abstract
An optical implementation of a single-layer, second-order neural network is presented. The quadratic products are obtained by passing the optical beam twice through the input ferroelectric liquid-crystal (FLC) spatial light modulator (SLM), with the interconnection weights being implemented by a further two-dimensional 128 × 128 FLC SLM. The machine successfully associates eight randomly chosen pattern–target pairs (dimensions 16 and 4, respectively) and can learn the parity association. Translation invariance is also demonstrated. Results from a computer model indicate that input SLM contrast ratios of 4:1 and electronic noise of 10% of the maximum output can be tolerated.Keywords
This publication has 3 references indexed in Scilit:
- Optical Connectionist Machine With Polarization-Based Bipolar Weight ValuesOptical Engineering, 1989
- Learning, invariance, and generalization in high-order neural networksApplied Optics, 1987
- Generation of Lyman-α radiation in phase-matched rare-gas mixturesOptics Letters, 1980