Abstract
Optical implementations of one-layer, perceptron-like neural networks have been shown to be very successful at associating pattern/target sets despite large system errors [1,2]. It has also been shown that large systems can be realized with such architectures (≥4 x 104 interconnections [2,3]), and appreciable processing speeds have been demonstrated (>108 interconnections/sec [4]). However, single layer networks are limited due to their inability to associate patterns that are not linearly separable. A more general network is the two layer network, which is able to model arbitrary functions, and create any decision boundary within the input vector pattern space [5]. In order to implement such a network, it is necessary to perform a nonlinearity at the hidden layer before performing a subsequent matrix multiplication. In general, optical materials performing fast nonlinear processing require high optical powers. Hybrid opto-electronic devices can perform nonlinear operations at moderate speeds and low optical powers [6].
© 1991 Optical Society of America
PDF ArticleMore Like This
Soo-Young Lee, Hyuek-Jae Lee, and Sang-Yung Shin
ME10 Optical Computing (IP) 1991
Michael G. Robinson, Lin Zhang, Kristina M. Johnson, and David A. Jared
MVV9 OSA Annual Meeting (FIO) 1990
Joshua Alspector
WB1 Optical Computing (IP) 1991