OPTICAL IMPLEMENTATION OF A TRANSLATION-INVARIANT 2ND-ORDER NEURAL-NETWORK FOR MULTIPLE-PATTERN CLASSIFICATION

A novel approach to the optical implementation of second-order neural networks that can recognize multiple patterns is reported. The systems issues, especially the accuracy required for the weighted interconnec tions, are discussed for numeric character (0-9) recognition. It is sh own that the accuracy of the weighted interconnections has a far great er influence on the network performance during training than on classi fication. To lessen the problem, we introduce an adaptive learning rul e, whereby the optical power is adjusted during training. Finally, num eric character recognition using an experimental system with a liquid- crystal display is demonstrated.