Design of an optical fixed-weight learning neural network

Authors

A. Steven Younger, MSU Graduate Student
Emmett Redd, Missouri State UniversityFollow

Abstract

This paper deals with the design, analysis, and simulation of a prototype Optical Fixed-Weight Learning Neural Network. This type of network could have learning rates five orders of magnitude faster than networks based on Von-Neumann platforms. This network has an embedded learning algorithm and dynamically learns new mappings by changing recurrent neural signal strengths. This will greatly speed up optical neural network learning since the medium containing the synaptic weights does not change during learning. Software simulations suggest that this design is sound. The physical implementation and evaluation of the prototype will be reported elsewhere.

Department(s)

Physics, Astronomy, and Materials Science

Document Type

Conference Proceeding

DOI

https://doi.org/10.1109/IJCNN.2005.1555901

Publication Date

12-1-2005

Recommended Citation

Younger, A. Steven, and Emmett Redd. "Design of an optical fixed-weight learning neural network." In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., vol. 1, pp. 610-615. IEEE, 2005.

Journal Title

Proceedings of the International Joint Conference on Neural Networks