An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories
-
- 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
-
- Neural Computation
-
Neural Computation 2 (4), 490-501, 1990-12
MIT Press - Journals
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1363388844078312832
-
- NII論文ID
- 30035678259
-
- ISSN
- 1530888X
- 08997667
-
- データソース種別
-
- Crossref
- CiNii Articles