Abstract
The finite impulse response neural network is described in detail. Different algorithms capable of temporal back-propagation are considered, including a novel modification to the conventional algorithm, called the delayed-feedback back-propagation algorithm. We present and analyze different optoelectronic processors making use of adaptive volume holograms and three-dimensional optical processing. Two single-layer architectures are presented: the input delay plane architecture and the output delay plane architecture. By combining them it is possible to implement both forward and backward propagation in two multi-layer architectures: the first making use of the conventional temporal back-propagation and the second making use of delayed-feedback back-propagation.
© 2002 Optical Society of America
Full Article | PDF ArticleMore Like This
Paulo E. X. Silveira, Gour S. Pati, and Kelvin H. Wagner
Appl. Opt. 43(35) 6421-6439 (2004)
Emmanuel Anemogiannis and Richard P. Kenan
Appl. Opt. 29(24) 3497-3502 (1990)
Yuri Owechko
Appl. Opt. 26(23) 5104-5111 (1987)