We have constructed an optical neural-network system with learning capability by using a Pockels readout optical modulator. The system has a two-dimensional structure that permits easy optical alignment and can handle images without scanning. Learning signals are calculated optically with two liquid-crystal devices by a matrix–matrix outer-product method. The calculated learning signals are added directly to the weights memorized on the Pockels readout optical modulator. A two-layer network is implemented, and the learning and recognition of four alphabetical characters are realized according to the delta rule.
© 1998 Optical Society of America
Masahiko Mori, Yutaka Yagai, Toyohiko Yatagai, and Masanobu Watanabe, "Optical Learning Neural Network with a Pockels Readout Optical Modulator," Appl. Opt. 37, 2852-2857 (1998)