Optical neural network for engineering design

摘要

An optical neural-network architecture is proposed that captures engineering design expertise and makes it available to designers. The network and its use as an associative memory are described. A novel fast learning algorithm is shown to be orders-of-magnitude faster than backpropagation. Reasons are presented for the feasibility of an optical implementation that uses novel optical devices. A structural example illustrates how engineering design expertise is captured and recovered from the network.