Title :
Learning algorithms for optical multilayer neural networks
Author :
Qiao, Yong ; Psaltis, Demetri
Author_Institution :
Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
Abstract :
Two issues related to the optical implementation of feedforward multilayer neural networks are discussed. First, an anti-Hebbian local learning rule is introduced to eliminate the need for error backpropagation in network training, as required by the commonly used back error propagation algorithm. Second, the effect of using square-law detectors in optical neural networks is considered, and an orthogonal vector algorithm is proposed to train such networks. While the first algorithm significantly reduces the complexity of optical neural networks, the second algorithm enables use of simple square-law optical detectors to implement neurons. Preliminary simulations have shown that not only are these two algorithms capable of solving typical pattern recognition problems, but they are also computationally effective
Keywords :
learning systems; neural nets; optical information processing; feedforward multilayer neural networks; learning algorithms; local learning rule; network training; optical multilayer neural networks; optical neural networks; orthogonal vector algorithm; pattern recognition; square-law detectors; Backpropagation algorithms; Feedforward neural networks; Multi-layer neural network; Neural networks; Neurons; Optical computing; Optical detectors; Optical fiber networks; Optical propagation; Optical superlattices;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155222