Abstract
A new approach to self-aligning unsupervised optical learning based on the competitive learning algorithm and adaptive holographic interconnections is introduced. A volume hologram is used to diffract the light from an input spatial light modulator so that it focuses upon a custom winner-take-all very-large-scale-integrated circuit liquid-crystal spatial light modulator. The units that receive the most light switch to a reflective state, and the light reflected from the winning pixels interferes in the volume of the dynamic hologram with the phase conjugate of the input pattern in order to add an outer-product perturbation to the current holographic interconnection. As a set of input patterns is cycled through many times, the system learns to diffract the light from a particular input class upon a self-organized set of detectors that recognize similar input patterns without the aid of a teacher or any required alignment. Beam-propagation simulations are used to show that the holographic optical learning network faithfully reproduces the behavior of the ideal competitive learning algorithm. A winner-take-all detector/modulator device containing a total of 576 optical neurons grouped into 31 separate competitive patches in the required sparse-grid topology has been successfully fabricated, and experimental results are presented.
© 1993 Optical Society of America
Full Article | PDF ArticleMore Like This
Alain Bergeron, Henri H. Arsenault, Erik Eustache, and Denis Gingras
Appl. Opt. 33(8) 1463-1468 (1994)
Kelvin Wagner and Demetri Psaltis
Appl. Opt. 26(23) 5061-5076 (1987)
Timothy M. Slagle and Kelvin Wagner
Opt. Lett. 17(16) 1164-1166 (1992)