Jump to content

Talk:Ronald J. Williams

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

Untitled

[edit]

Much more could be said about Ronald J. Williams; I just mentioned that he is professor of computer science at Northeastern University, and one of the pioneers of neural networks. He co-authored a paper on the backpropagation algorithm which triggered a boom in neural network research[1]. He also made fundamental contributions to the fields of recurrent neural networks[2][3] and reinforcement learning[4].

References

[edit]
  1. ^ David E. Rumelhart, Geoffrey E. Hinton und Ronald J. Williams. Learning representations by back-propagating errors., Nature (London) 323, S. 533-536
  2. ^ Williams, R. J. and Zipser, D. (1989). A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1, 270-280.
  3. ^ R. J. Williams and D. Zipser. Gradient-based learning algorithms for recurrent networks and their computational complexity. In Back-propagation: Theory, Architectures and Applications. Hillsdale, NJ: Erlbaum, 1994.
  4. ^ Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8, 229-256.
[edit]

Epsiloner (talk) 16:33, 7 July 2010 (UTC)[reply]