MURAL - Maynooth University Research Archive Library



    Dynamic recurrent neural networks


    Pearlmutter, Barak A. (1990) Dynamic recurrent neural networks. Technical Report. Carnegie Mellon University. (Unpublished)

    [img]
    Preview
    Download (1MB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    We survey learning algorithms for recurrent neural networks with hidden units and attempt to put the various techniques into a common framework. We discuss fixpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non-fixpoint algorithms, namely backpropagation through time, Elman's history cutoff nets, and Jordan's output feedback architecture. Forward propagation, an online technique that uses adjoint equations, is also discussed. In many cases, the unified presentation leads to generalizations of various sorts. Some simulations are presented, and at the end, issues of computational complexity are addressed.

    Item Type: Monograph (Technical Report)
    Keywords: Dynamic; recurrent; neural; networks;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 5505
    Depositing User: Barak Pearlmutter
    Date Deposited: 15 Oct 2014 13:32
    Publisher: Carnegie Mellon University
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year