Carsten Peterson, Stephen Redfield, James Keeler, Eric Hartman
Optical Engineering, Vol. 29, Issue 04, (April 1990) https://doi.org/10.1117/12.55604
TOPICS: Crystals, Neural networks, Machine learning, Multiplexing, Neurons, Laser crystals, Spatial light modulators, Algorithms, Computer simulations, Absorption
We present a novel, versatile optoelectronic neural network architecture
for implementing supervised learning algorithms in photorefractive
materials. The system is based on spatial multiplexing rather than
the more commonly used angular multiplexing of the interconnect gratings.
This simple, single-crystal architecture implements a variety of multilayer
supervised learning algorithms including mean field theory, backpropagation,
and Marr-Albus-Kanerva style algorithms. Extensive simulations
show how beam depletion, rescattering, absorption, and decay
effects of the crystal are compensated for by suitably modified supervised
learning algorithms.