Adaptive holographic implementation of a neural network

John D. Downie; Butler P. Hine III; Max B. Reid

doi:10.1117/12.19617

Translator Disclaimer

1 July 1990 Adaptive holographic implementation of a neural network

John D. Downie, Butler P. Hine III, Max B. Reid

Author Affiliations +

Proceedings Volume 1247, Nonlinear Image Processing; (1990) https://doi.org/10.1117/12.19617
Event: Electronic Imaging: Advanced Devices and Systems, 1990, Santa Clara, CA, United States

Abstract

A holographic implementation for neural networks is proposed and demonstrated as an alternative to the optical matrix-vector multiplier architecture. In comparison, the holographic architecture makes more efficient use of the system space-bandwidth product for certain types of neural networks. The principal network component is a thermoplastic hologram, used to provide both interconnection weights and beam redirection. Given the updatable nature of this type of hologram, adaptivity or network learning is possible in the optical system. Two networks with fixed weights are experimentally implemented and verified, and for one of these examples we demonstrate the advantage of the holographic implementation with respect to the matrix-vector processor.

Citation Download Citation

John D. Downie, Butler P. Hine III, and Max B. Reid "Adaptive holographic implementation of a neural network", Proc. SPIE 1247, Nonlinear Image Processing, (1 July 1990); https://doi.org/10.1117/12.19617

ACCESS THE FULL ARTICLE