Abstract
Coherent optical neural networks that have optical-frequency-controlled behavior are proposed as sophisticated optical neural systems. The coherent optical neural-network system consists of an optical complex-valued neural network, a phase reference path, and coherent detectors for self-homodyne detection. The learning process is realized by adjusting the delay time and the transparency of neural connections in the optical neural network with the optical frequency as a learning parameter. Generalization ability in frequency space is also analyzed. Information geometry in the learning process is discussed for obtaining a parameter range in which a reasonable generalization is realized in frequency space. It is found that there are error-function minima periodically both in the delay-time domain and the input-signal-frequency domain. Because of this reason, the initial connection delay should be within a certain range for a meaningful generalization. Simulation experiments demonstrate that a stable learning and a reasonable generalization in the frequency domain are successfully realized in a parameter range obtained in the theory.
© 1996 Optical Society of America
Full Article | PDF ArticleMore Like This
Sotaro Kawata and Akira Hirose
Opt. Lett. 28(24) 2524-2526 (2003)
Sotaro Kawata and Akira Hirose
Appl. Opt. 44(19) 4053-4059 (2005)
Gregory C. Petrisor, Adam A. Goldstein, B. Keith Jenkins, Edward J. Herbulock, and Armand R. Tanguay
Appl. Opt. 35(8) 1328-1343 (1996)