We report the optical implementation of a neural network based on a nearest matched filter algorithm and extensive lateral inhibition. Extremely rapid learning is demonstrated in pattern recognition and autonomous control applications, without introducing processing artifacts such as spurious states and ambiguous solutions. The optical implementation is achieved with a reconfigurable, bipolar mask-type crossbar switch based on an inexpensive liquid crystal spatial light modulator.
© 1989 Optical Society of America
Peter J. de Groot and Robert J. Noll, "Adaptive neural network in a hybrid optical/electronic architecture using lateral inhibition," Appl. Opt. 28, 3852-3859 (1989)