[OPTICAL REVIEW Vol. 4, No. 4 (1997) 465-470]
Optical Learning Neural Network Using Photorefractive Waveguides
Osamu MATOBA,1,* Kazuyoshi ITOH1 and Yoshiki ICHIOKA2
1Department of Applied Physics, 2Department of Material and Life Science, Graduate School of Engineering, Osaka University, Yamadaoka, 2-1, Suita, Osaka, 565 Japan
(Received September 26, 1996; Accepted May 7, 1997)
A model of an optical neural network with learning ability is proposed. We numerically evaluate the learning ability of the proposed network by using parameters determined by experiments. Adaptive connections between artificial neurons are implemented using photorefractive (PR) waveguides that can be optically modified by guided beams. The network consists of three layers and has bipolar weights within the limited range. The bipolar weight is encoded as the difference between optical power transmittances of signal beams in two channels of the PR waveguides. The adaptivity of the transmittance of PR waveguide is experimentally evaluated and is incorporated into the proposed network simulated in a computer. The proposed network is trained by a simplified local learning algorithm. Numerical results showed that the proposed three-layered network with six hidden neurons can solve the exclusive-or problem.
Key words : optical neural network, optical learning, photorefractive effect, waveguide, optical interconnection