• Login
    View Item 
    •   Shocker Open Access Repository Home
    • Engineering
    • Electrical Engineering and Computer Science
    • EECS Faculty Scholarship
    • EECS Research Publications
    • View Item
    •   Shocker Open Access Repository Home
    • Engineering
    • Electrical Engineering and Computer Science
    • EECS Faculty Scholarship
    • EECS Research Publications
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

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

    View/Open
    Skinner_2000 (20.69Kb)
    Date
    2000-11
    Author
    Cruz-Cabrera, A.A.
    Yang, Mingtao
    Cui, Guogi
    Behrman, Elizabeth C.
    Steck, James E.
    Skinner, Steven R.
    Metadata
    Show full item record
    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"
    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.
    Description
    Click on the DOI link below to access the article (may not be free)
    URI
    http://hdl.handle.net/10057/4438
    http://dx.doi.org/10.1109/72.883476
    Collections
    • AE Research Publications
    • EECS Research Publications
    • PHY Research Publications (from 2011)

    Browse

    All of Shocker Open Access RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsBy TypeThis CollectionBy Issue DateAuthorsTitlesSubjectsBy Type

    My Account

    LoginRegister

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    DSpace software copyright © 2002-2023  DuraSpace
    DSpace Express is a service operated by 
    Atmire NV