Reinforcement and backpropagation training for an optical neural network using self-lensing effects

SOAR Repository

Show simple item record

dc.contributor Wichita State University. Electrical Engineering and Computer Science
dc.contributor.author Cruz-Cabrera, A.A.
dc.contributor.author Yang, Mingtao
dc.contributor.author Cui, Guogi
dc.contributor.author Behrman, Elizabeth C.
dc.contributor.author Steck, James E.
dc.contributor.author Skinner, Steven R.
dc.date.accessioned 2012-02-10T18:19:55Z
dc.date.available 2012-02-10T18:19:55Z
dc.date.issued 2000-11
dc.identifier.citation "Cruz-Cabrera AA, M Yang, G Cui, EC Behrman, JE Steck, and SR Skinner. 2000. ""Reinforcement and backpropagation training for an optical neural network using self-lensing effects"". IEEE Transactions on Neural Networks / a Publication of the IEEE Neural Networks Council. 11 (6): 1450-7. doi: 10.1109/72.883476" en_US
dc.identifier.issn 1045-9227
dc.identifier.issn 1941-0093
dc.identifier.uri http://hdl.handle.net/10057/4438
dc.identifier.uri http://dx.doi.org/10.1109/72.883476
dc.description Click on the DOI link below to access the article (may not be free) en_US
dc.description.abstract The optical bench training of an optical feedforward neural network, developed by the authors, is presented. The network uses an optical nonlinear material for neuron processing and a trainable applied optical pattern as the network weights. The nonlinear material, with the applied weight pattern, modulates the phase front of a forward propagating information beam by dynamically altering the index of refraction profile of the material. To verify that the network can be trained in real time, six logic gates were trained using a reinforcement training paradigm. More importantly, to demonstrate optical backpropagation, three gates were trained via optical error backpropagation. The output error is optically backpropagated, detected with a CCD camera, and the weight pattern is updated and stored on a computer. The obtained results lay the ground work for the implementation of multilayer neural networks that are trained using optical error backpropagation and are able to solve more complex problems. en_US
dc.language.iso en_US en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Neural Networks, IEEE Transactions on;2000:, v.11, no.6
dc.subject Backpropagation en_US
dc.subject Experimental en_US
dc.subject Feedforward en_US
dc.subject Hardware en_US
dc.subject Neural networks en_US
dc.subject Nonlinear optics en_US
dc.subject Optical en_US
dc.title Reinforcement and backpropagation training for an optical neural network using self-lensing effects en_US
dc.type Article en_US
dc.description.version Peer reviewed
dc.rights.holder Copyright © 2000, IEEE

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search SOAR

Advanced Search


My Account