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
Original Manuscript: August 13, 2001
Revised Manuscript: February 25, 2002
Published: July 10, 2002
Paulo E. X. Silveira, G. S. Pati, and Kelvin H. Wagner, "Optical finite impulse response neural networks," Appl. Opt. 41, 4162-4180 (2002)