Optical information processing based on an associative-memory model of neural nets with thresholding and feedback

TLDR

The Hopfield model exhibits collective computational properties such as pattern recognition from partial inputs, robustness, and error‑correction. Its optical implementation is attractive due to specific features, and the paper outlines several optical schemes. The paper reviews the Hopfield model’s collective computational properties. Published in Proc.

Abstract

The remarkable collective computational properties of the Hopfield model for neural networks [Proc. Nat. Acad. Sci. USA 79, 2554 (1982)] are reviewed. These include recognition from partial input, robustness, and error-correction capability. Features of the model that make its optical implementation attractive are discussed, and specific optical implementation schemes are given.