Abstract
The discrete-valued neural network proposed by Hopfield requires zero-diagonal terms in the memory matrix so that the net evolves toward a local minimum of an energy function. For a version of this model with bipolar nodes and positive terms along the diagonal, the net evolves so that only updates that lower the energy by a sufficient amount are accepted. For a net programmed as an outer-product associative content-addressable memory with randomly coded memories, the version with nonzero-diagonal elements performs nearly identically to one with zero-diagonal terms. The dropping of the zero-diagonal requirement may be advantageous for optical implementation in that it allows the memory to configure as a cascade of an inner product operation and weighted summation operation and does not require explicit update of the connectivity matrix.
© 1987 Optical Society of America
PDF ArticleMore Like This
Soo-Young Lee, Chang-Sup Shim, Ju-Seog Jang, and Sang-Yung Shin
FB7 OSA Annual Meeting (FIO) 1987
Jack Y. Jau, Y. Fainman, and Sing H. Lee
TuA7 Optical Computing (IP) 1987
A. Von Lehmen, E. G. Paek, L. C. Carrion, J. S. Patel, and A. Marrakchi
WU2 OSA Annual Meeting (FIO) 1989