2 February 1993 Optical neural networks using a new radial nonlinear neural layer
Author Affiliations +
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.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kelvin H. Wagner, Kelvin H. Wagner, Michael Mozer, Michael Mozer, Paul Smolensky, Paul Smolensky, Yoshiro Miyata, Yoshiro Miyata, Mike Fellows, Mike Fellows, } "Optical neural networks using a new radial nonlinear neural layer", Proc. SPIE 1773, Photonics for Computers, Neural Networks, and Memories, (2 February 1993); doi: 10.1117/12.983192; https://doi.org/10.1117/12.983192
PROCEEDINGS
PAGES


SHARE
RELATED CONTENT

New dimensions in D-STOP neural systems
Proceedings of SPIE (November 08 1993)
Optoelectronic neuron implementation
Proceedings of SPIE (February 22 2005)
Buried metalic object identification by EMI sensor
Proceedings of SPIE (April 25 2007)

Back to Top