25,161
edits
Changes
Created page with "'''Home * People * Christopher Clark''' FILE:ChristopherClark.jpg|border|right|thumb|240px|link=https://allenai.org/visitors.html| Christopher Clark <ref..."
'''[[Main Page|Home]] * [[People]] * Christopher Clark'''
[[FILE:ChristopherClark.jpg|border|right|thumb|240px|link=https://allenai.org/visitors.html| Christopher Clark <ref>[https://allenai.org/visitors.html Visiting Scholars — Allen Institute for AI]</ref> ]]
'''Christopher Clark''',<br/>
an American computer scientist and researcher at [https://en.wikipedia.org/wiki/Allen_Institute_for_AI Allen Institute for Artificial Intelligence], [https://en.wikipedia.org/wiki/Seattle Seattle], [https://en.wikipedia.org/wiki/Washington_(state) Washington], and Ph.D. student at the [https://en.wikipedia.org/wiki/University_of_Washington University of Washington].
He received a M.Sc. in [[Artificial Intelligence|artificial intelligence]] from the [[University of Edinburgh]], where he studied [[learning|machine learning]]
and completed a thesis on using [[Neural Networks#Convolutional|deep convolutional neural networks]] for the game of [[Go]] to [[Deep Learning|learn]] and predict the moves made by expert Go players.
=DCNNs in Go=
As reported in their 2014 paper ''Teaching Deep Convolutional Neural Networks to Play Go'', Clark and [[Amos Storkey]] trained an 8-layer [[Go#CNN|convolutional neural network]] <ref>[https://en.wikipedia.org/wiki/Convolutional_neural_network#Playing_Go Convolutional neural network - Playing Go - Wikipedia]</ref> by [[Supervised Learning|supervised learning]] from a database of human professional games to predict the moves made by expert [[Go]] players.
They introduced a number of novel techniques, including a method of tying weights in the network to 'hard code' symmetries that are expect to exist in the target function,
and demonstrated in an ablation study they considerably improve performance. Their final networks can consistently defeat [[Gnu Go]], indicating it is state of the art among programs that do not use [[Monte-Carlo Tree Search]],
and was also able to win some games against [https://www.game-ai-forum.org/icga-tournaments/program.php?id=535 Fuego] while using a fraction of the playing time
<ref>[[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [http://arxiv.org/abs/1412.3409 arXiv:1412.3409]</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007010.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 14, 2014</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007041.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>
<ref>[https://www.technologyreview.com/s/533496/why-neural-networks-look-set-to-thrash-the-best-human-go-players-for-the-first-time/ Why Neural Networks Look Set to Thrash the Best Human Go Players for the First Time] | [https://en.wikipedia.org/wiki/MIT_Technology_Review MIT Technology Review], December 15, 2014</ref>
<ref>[http://www.talkchess.com/forum/viewtopic.php?t=54663 Teaching Deep Convolutional Neural Networks to Play Go] by [[Michel Van den Bergh]], [[CCC]], December 16, 2014</ref>
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/c/Clark:Christopher dblp: Christopher Clark]</ref>
* [[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]
* [[Christopher Clark]], [[Amos Storkey]] ('''2015'''). ''Training Deep Convolutional Neural Networks to Play Go''. [https://dblp.uni-trier.de/db/conf/icml/icml2015.html ICML 2015], [http://proceedings.mlr.press/v37/clark15.pdf pdf]
=External Links=
* [https://www.research.ed.ac.uk/portal/en/clippings/christopher-clark-and-amos-storkey-apply-new-algorithms-to-ancient-chinese-game-go(75c8bf11-aab5-467a-8c73-a1f04022bdab).html Christopher Clark and Amos Storkey apply new algorithms to ancient Chinese game 'Go' - Edinburgh Research Explorer]
* [http://videolectures.net/christopher_clark/ Christopher Clark - Allen Institute for Artificial Intelligence (AI2) - VideoLectures.NET]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Clark]]
[[Category:Go Programmer|Clark]]
[[FILE:ChristopherClark.jpg|border|right|thumb|240px|link=https://allenai.org/visitors.html| Christopher Clark <ref>[https://allenai.org/visitors.html Visiting Scholars — Allen Institute for AI]</ref> ]]
'''Christopher Clark''',<br/>
an American computer scientist and researcher at [https://en.wikipedia.org/wiki/Allen_Institute_for_AI Allen Institute for Artificial Intelligence], [https://en.wikipedia.org/wiki/Seattle Seattle], [https://en.wikipedia.org/wiki/Washington_(state) Washington], and Ph.D. student at the [https://en.wikipedia.org/wiki/University_of_Washington University of Washington].
He received a M.Sc. in [[Artificial Intelligence|artificial intelligence]] from the [[University of Edinburgh]], where he studied [[learning|machine learning]]
and completed a thesis on using [[Neural Networks#Convolutional|deep convolutional neural networks]] for the game of [[Go]] to [[Deep Learning|learn]] and predict the moves made by expert Go players.
=DCNNs in Go=
As reported in their 2014 paper ''Teaching Deep Convolutional Neural Networks to Play Go'', Clark and [[Amos Storkey]] trained an 8-layer [[Go#CNN|convolutional neural network]] <ref>[https://en.wikipedia.org/wiki/Convolutional_neural_network#Playing_Go Convolutional neural network - Playing Go - Wikipedia]</ref> by [[Supervised Learning|supervised learning]] from a database of human professional games to predict the moves made by expert [[Go]] players.
They introduced a number of novel techniques, including a method of tying weights in the network to 'hard code' symmetries that are expect to exist in the target function,
and demonstrated in an ablation study they considerably improve performance. Their final networks can consistently defeat [[Gnu Go]], indicating it is state of the art among programs that do not use [[Monte-Carlo Tree Search]],
and was also able to win some games against [https://www.game-ai-forum.org/icga-tournaments/program.php?id=535 Fuego] while using a fraction of the playing time
<ref>[[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [http://arxiv.org/abs/1412.3409 arXiv:1412.3409]</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007010.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 14, 2014</ref>
<ref>[http://computer-go.org/pipermail/computer-go/2014-December/007041.html Teaching Deep Convolutional Neural Networks to Play Go] by [[Hiroshi Yamashita]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], December 19, 2014</ref>
<ref>[https://www.technologyreview.com/s/533496/why-neural-networks-look-set-to-thrash-the-best-human-go-players-for-the-first-time/ Why Neural Networks Look Set to Thrash the Best Human Go Players for the First Time] | [https://en.wikipedia.org/wiki/MIT_Technology_Review MIT Technology Review], December 15, 2014</ref>
<ref>[http://www.talkchess.com/forum/viewtopic.php?t=54663 Teaching Deep Convolutional Neural Networks to Play Go] by [[Michel Van den Bergh]], [[CCC]], December 16, 2014</ref>
=Selected Publications=
<ref>[https://dblp.uni-trier.de/pers/hd/c/Clark:Christopher dblp: Christopher Clark]</ref>
* [[Christopher Clark]], [[Amos Storkey]] ('''2014'''). ''Teaching Deep Convolutional Neural Networks to Play Go''. [https://arxiv.org/abs/1412.3409 arXiv:1412.3409]
* [[Christopher Clark]], [[Amos Storkey]] ('''2015'''). ''Training Deep Convolutional Neural Networks to Play Go''. [https://dblp.uni-trier.de/db/conf/icml/icml2015.html ICML 2015], [http://proceedings.mlr.press/v37/clark15.pdf pdf]
=External Links=
* [https://www.research.ed.ac.uk/portal/en/clippings/christopher-clark-and-amos-storkey-apply-new-algorithms-to-ancient-chinese-game-go(75c8bf11-aab5-467a-8c73-a1f04022bdab).html Christopher Clark and Amos Storkey apply new algorithms to ancient Chinese game 'Go' - Edinburgh Research Explorer]
* [http://videolectures.net/christopher_clark/ Christopher Clark - Allen Institute for Artificial Intelligence (AI2) - VideoLectures.NET]
=References=
<references />
'''[[People|Up one level]]'''
[[Category:Researcher|Clark]]
[[Category:Go Programmer|Clark]]
