25,161
edits
Changes
Created page with "'''Home * People * Chris J. Maddison''' FILE:ChrisJMaddison.jpg|border|right|thumb|link=http://scholar.google.ca/citations?user=WjCG3owAAAAJ| Chris J. Ma..."
'''[[Main Page|Home]] * [[People]] * Chris J. Maddison'''
[[FILE:ChrisJMaddison.jpg|border|right|thumb|link=http://scholar.google.ca/citations?user=WjCG3owAAAAJ| Chris J. Maddison <ref>[http://scholar.google.ca/citations?user=WjCG3owAAAAJ Chris J. Maddison - Google Scholar Citations]</ref> ]]
'''Chris J. Maddison''',<br/>
a Canadian computer scientist affiliated with the [[University of Toronto]]. His reaearch interests include [[Learning|machine learning]], [[Neural Networks|neural networks]], [[Deep Learning|deep learning]], [https://en.wikipedia.org/wiki/Inference inference], [https://en.wikipedia.org/wiki/Monte_Carlo_method Monte Carlo methods], and how can we simulate complex models of the world <ref>[http://www.cs.toronto.edu/~cmaddis/ Chris J. Maddison]</ref>.
=DCNNs in Go=
In their 2014 paper ''Move Evaluation in Go Using Deep Convolutional Neural Networks'' <ref>[[Chris J. Maddison]], [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], [[David Silver]] ('''2014'''). ''Move Evaluation in Go Using Deep Convolutional Neural Networks''. [http://arxiv.org/abs/1412.6564v1 arXiv:1412.6564v1]</ref>, Chris J. Maddison, [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], and [[David Silver]] investigate whether [[Go#CNN|deep convolutional neural networks]] can be used to directly represent and [[Deep Learning|learn]] a move evaluation function for the game of [[Go]]. They train a large 12-layer convolutional neural network by [[Supervised Learning|supervised learning]] from a database of human professional games. The network correctly predicted the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any [[Search|search]], it beat the traditional search program [[Gnu Go]] in 97% of games, and matched the performance of a state-of-the-art [[Monte-Carlo Tree Search]] that simulates a million positions per move <ref>[http://computer-go.org/pipermail/computer-go/2014-December/007046.html Move Evaluation in Go Using Deep Convolutional Neural Networks] by [[Shih-Chieh Huang|Aja Huang]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>.
=Selected Publications=
<ref>[http://dblp.uni-trier.de/pers/hd/m/Maddison:Chris_J= dblp: Chris J. Maddison]</ref>
* [http://dblp.uni-trier.de/pers/hd/g/Grosse:Roger_B= Roger B. Grosse], [[Chris J. Maddison]], [[Ruslan R. Salakhutdinov]] ('''2013'''). ''[http://papers.nips.cc/paper/4879-annealing-between-distributions-by-averaging-moments Annealing Between Distributions by Averaging Moments]''. [http://dblp.uni-trier.de/db/conf/nips/nips2013.html#GrosseMS13 NIPS 2013]
* [[Chris J. Maddison]], [http://scholar.google.com/citations?user=oavgGaMAAAAJ Daniel Tarlow], [http://scholar.google.co.uk/citations?user=odOmEY0AAAAJ Tom Minka] ('''2014'''). ''A* Sampling''. [http://arxiv.org/abs/1411.0030 arXiv:1411.0030]
* [[Chris J. Maddison]], [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], [[David Silver]] ('''2014'''). ''Move Evaluation in Go Using Deep Convolutional Neural Networks''. [http://arxiv.org/abs/1412.6564v1 arXiv:1412.6564v1]
* [[David Silver]], [[Shih-Chieh Huang|Aja Huang]], [[Chris J. Maddison]], [[Arthur Guez]], [[Laurent Sifre]], [[George van den Driessche]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Veda Panneershelvam]], [[Marc Lanctot]], [[Sander Dieleman]], [[Dominik Grewe]], [[John Nham]], [[Nal Kalchbrenner]], [[Ilya Sutskever]], [[Timothy Lillicrap]], [[Madeleine Leach]], [[Koray Kavukcuoglu]], [[Thore Graepel]], [[Demis Hassabis]] ('''2016'''). ''[http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html Mastering the game of Go with deep neural networks and tree search]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 529 » [[AlphaGo]]
=External Links=
* [http://www.cs.toronto.edu/~cmaddis/ Chris J. Maddison]
* [http://scholar.google.ca/citations?user=WjCG3owAAAAJ Chris J. Maddison - Google Scholar Citations]
* [https://www.utoronto.ca/news/google-deepminds-alphago-meet-u-t-computer-scientists-who-helped-it-win Google DeepMind's AlphaGo: meet the U of T computer scientists who helped it win], by [https://www.utoronto.ca/news/authors-reporters/nina-haikara Nina Haikara], [[University of Toronto|U of T news]], February 02, 2016
=References=
<references />
'''[[People|Up one level]]'''
[[FILE:ChrisJMaddison.jpg|border|right|thumb|link=http://scholar.google.ca/citations?user=WjCG3owAAAAJ| Chris J. Maddison <ref>[http://scholar.google.ca/citations?user=WjCG3owAAAAJ Chris J. Maddison - Google Scholar Citations]</ref> ]]
'''Chris J. Maddison''',<br/>
a Canadian computer scientist affiliated with the [[University of Toronto]]. His reaearch interests include [[Learning|machine learning]], [[Neural Networks|neural networks]], [[Deep Learning|deep learning]], [https://en.wikipedia.org/wiki/Inference inference], [https://en.wikipedia.org/wiki/Monte_Carlo_method Monte Carlo methods], and how can we simulate complex models of the world <ref>[http://www.cs.toronto.edu/~cmaddis/ Chris J. Maddison]</ref>.
=DCNNs in Go=
In their 2014 paper ''Move Evaluation in Go Using Deep Convolutional Neural Networks'' <ref>[[Chris J. Maddison]], [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], [[David Silver]] ('''2014'''). ''Move Evaluation in Go Using Deep Convolutional Neural Networks''. [http://arxiv.org/abs/1412.6564v1 arXiv:1412.6564v1]</ref>, Chris J. Maddison, [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], and [[David Silver]] investigate whether [[Go#CNN|deep convolutional neural networks]] can be used to directly represent and [[Deep Learning|learn]] a move evaluation function for the game of [[Go]]. They train a large 12-layer convolutional neural network by [[Supervised Learning|supervised learning]] from a database of human professional games. The network correctly predicted the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any [[Search|search]], it beat the traditional search program [[Gnu Go]] in 97% of games, and matched the performance of a state-of-the-art [[Monte-Carlo Tree Search]] that simulates a million positions per move <ref>[http://computer-go.org/pipermail/computer-go/2014-December/007046.html Move Evaluation in Go Using Deep Convolutional Neural Networks] by [[Shih-Chieh Huang|Aja Huang]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>.
=Selected Publications=
<ref>[http://dblp.uni-trier.de/pers/hd/m/Maddison:Chris_J= dblp: Chris J. Maddison]</ref>
* [http://dblp.uni-trier.de/pers/hd/g/Grosse:Roger_B= Roger B. Grosse], [[Chris J. Maddison]], [[Ruslan R. Salakhutdinov]] ('''2013'''). ''[http://papers.nips.cc/paper/4879-annealing-between-distributions-by-averaging-moments Annealing Between Distributions by Averaging Moments]''. [http://dblp.uni-trier.de/db/conf/nips/nips2013.html#GrosseMS13 NIPS 2013]
* [[Chris J. Maddison]], [http://scholar.google.com/citations?user=oavgGaMAAAAJ Daniel Tarlow], [http://scholar.google.co.uk/citations?user=odOmEY0AAAAJ Tom Minka] ('''2014'''). ''A* Sampling''. [http://arxiv.org/abs/1411.0030 arXiv:1411.0030]
* [[Chris J. Maddison]], [[Shih-Chieh Huang|Aja Huang]], [[Ilya Sutskever]], [[David Silver]] ('''2014'''). ''Move Evaluation in Go Using Deep Convolutional Neural Networks''. [http://arxiv.org/abs/1412.6564v1 arXiv:1412.6564v1]
* [[David Silver]], [[Shih-Chieh Huang|Aja Huang]], [[Chris J. Maddison]], [[Arthur Guez]], [[Laurent Sifre]], [[George van den Driessche]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Veda Panneershelvam]], [[Marc Lanctot]], [[Sander Dieleman]], [[Dominik Grewe]], [[John Nham]], [[Nal Kalchbrenner]], [[Ilya Sutskever]], [[Timothy Lillicrap]], [[Madeleine Leach]], [[Koray Kavukcuoglu]], [[Thore Graepel]], [[Demis Hassabis]] ('''2016'''). ''[http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html Mastering the game of Go with deep neural networks and tree search]''. [https://en.wikipedia.org/wiki/Nature_%28journal%29 Nature], Vol. 529 » [[AlphaGo]]
=External Links=
* [http://www.cs.toronto.edu/~cmaddis/ Chris J. Maddison]
* [http://scholar.google.ca/citations?user=WjCG3owAAAAJ Chris J. Maddison - Google Scholar Citations]
* [https://www.utoronto.ca/news/google-deepminds-alphago-meet-u-t-computer-scientists-who-helped-it-win Google DeepMind's AlphaGo: meet the U of T computer scientists who helped it win], by [https://www.utoronto.ca/news/authors-reporters/nina-haikara Nina Haikara], [[University of Toronto|U of T news]], February 02, 2016
=References=
<references />
'''[[People|Up one level]]'''
