Goldstein AA, Petrisor GC, Jenkins BK. Gain and exposure scheduling to compensate for photorefractive neural-network weight decay.
OPTICS LETTERS 1995;
20:611-613. [PMID:
19859272 DOI:
10.1364/ol.20.000611]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/28/2023]
Abstract
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-Hoff, perceptron) is presented. This schedule compensates for photorefractive diffraction-efficiency decay by iteratively increasing the spatial-light-modulator transfer function gain and decreasing the weight-update exposure time. Simulation results for the scheduling procedure, as applied to backpropagation learning for the exclusive-OR problem, show improved learning performance compared with results for networks trained without scheduling.
Collapse