Share Email Print

Proceedings Paper

Optical neural networks using a new radial nonlinear neural layer
Author(s): Kelvin H. Wagner; Michael Mozer; Paul Smolensky; Yoshiro Miyata; Mike Fellows
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Radially nonlinear neurons are introduced, and back propagation learning for multilayer networks of these simple hidden units is derived and simulated. The nonlinear transformation performed by a hidden layer of radial units can be represented as a simple multiplication of the summed net input to each neuron by a single value which is only dependent on the total input to the hidden layer. This allows a simple optical implementation, in which a single modulator/detector is able to act as an entire hidden layer by multiplexing the neuron net inputs and processed outputs.

Paper Details

Date Published: 2 February 1993
Proc. SPIE 1773, Photonics for Computers, Neural Networks, and Memories, (2 February 1993); doi: 10.1117/12.983192
Show Author Affiliations
Kelvin H. Wagner, Univ. of Colorado/Boulder (United States)
Michael Mozer, Univ. of Colorado/Boulder (United States)
Paul Smolensky, Univ. of Colorado/Boulder (United States)
Yoshiro Miyata, Univ. of Colorado/Boulder (United States)
Mike Fellows, Univ. of Colorado/Boulder (United States)

Published in SPIE Proceedings Vol. 1773:
Photonics for Computers, Neural Networks, and Memories
Stephen T. Kowel; John A. Neff; William J. Miceli, Editor(s)

© SPIE. Terms of Use
Back to Top