Catastrophic forgetting and capacity saturation are the central challenges">

    Toward Training Recurrent Neural Networks for Lifelong Learning

    Shagun Sodhani
    Shagun Sodhani
    Sarath Chandar
    Sarath Chandar

    Neural computation, pp. 1-35, 2019.

    Cited by: 0|Bibtex|Views89|Links
    WOS EI

    Abstract:

    <para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent neural...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments