An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

DOI Web Site 被引用文献8件
  • Ronald J. Williams
    College of Computer Science, Northeastern University, Boston, MA 02115 USA
  • Jing Peng
    College of Computer Science, Northeastern University, Boston, MA 02115 USA

抄録

<jats:p> A novel variant of the familiar backpropagation-through-time approach to training recurrent networks is described. This algorithm is intended to be used on arbitrary recurrent networks that run continually without ever being reset to an initial state, and it is specifically designed for computationally efficient computer implementation. This algorithm can be viewed as a cross between epochwise backpropagation through time, which is not appropriate for continually running networks, and the widely used on-line gradient approximation technique of truncated backpropagation through time. </jats:p>

収録刊行物

被引用文献 (8)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ