Abstract
An adaptive neural-network architecture is presented that incorporates (1) a simultaneous incoherent/coherent holographic recording and reconstruction technique that permits simultaneous updates of all weights in a multiplexed volume holographic interconnection during each iteration of a neural learning algorithm1; (2) a double-angle multiplexing arrangement in which each pixel of the object-beam spatial light modulator (SLM) is illuminated by a set of mutually incoherent beams, each at a different angle; and (3) optoelectronic SLM's for the neural input and training planes, each with dualchannel inputs and outputs.2 The architecture incorporates modularity; capability for lateral, feedforward, and feedback interconnections in a multilayer network; effectively bipolar signals and weights; and capacity to implement a variety of network models and supervised or unsupervised learning algorithms. Results of computer simulations and laboratory experiments on selected aspects of the architecture will also be presented.
© 1990 Optical Society of America
PDF ArticleMore Like This
P. Asthana, H. Chin, G. Nordin, A. R. Tanguay, G. C. Petrisor, B. K. Jenkins, and A. Madhukar
MVV4 OSA Annual Meeting (FIO) 1990
B. Keith Jenkins, Armand R. Tanguay, Anupam Madhukar, and Christoph von der Malsburg
MBB1 OSA Annual Meeting (FIO) 1992
G. C. Petrisor, B. K. Jenkins, H. Chin, and A. R. Tanguay
MVV1 OSA Annual Meeting (FIO) 1990