Aa. Goldstein et al., GAIN AND EXPOSURE SCHEDULING TO COMPENSATE FOR PHOTOREFRACTIVE NEURAL-NETWORK WEIGHT DECAY, Optics letters, 20(6), 1995, pp. 611-613
A gain and exposure schedule that theoretically eliminates the effect
of photorefractive weight decay for the general class of outer-product
neural-network learning algorithms (e.g., backpropagation, Widrow-Hof
f, perceptron) is presented. This schedule compensates for photorefrac
tive diffraction-efficiency decay by iteratively increasing the spatia
l-light-modulator transfer function gain and decreasing the weight-upd
ate exposure time. Simulation results for the scheduling procedure, as
applied to backpropagation learning for the exclusive-OR problem, sho
w improved learning performance compared with results for networks tra
ined without scheduling.