Abstract
Associative memory based on the Hopfield model utilizing interconnections by multiple optical fiber nets is proposed and demonstrated experimentally. The coupling ratio from fiber to fiber represents the synaptic weight of the connection between units. The remarkable feature of the optical fiber neural networks is that global connections between 2-D units can be easily achieved, resulting in simultaneous multiplication of the weight matrix and input vector. In the experiment, multiple fiber nets having 252 connections for 5 × 5 binary patterns are prepared, and three patterns are stored and successfully retrieved.
© 1989 Optical Society of America
Full Article | PDF ArticleMore Like This
Sheng L. Yeh, Rong C. Lo, and Cha Y. Shi
Appl. Opt. 43(4) 858-865 (2004)
Nabil H. Farhat, Demetri Psaltis, Aluizio Prata, and Eung Paek
Appl. Opt. 24(10) 1469-1475 (1985)
Taiwei Lu, Shudong Wu, Xin Xu, and Francis T. S. Yu
Appl. Opt. 28(22) 4908-4913 (1989)