25,161
edits
Changes
Go
,no edit summary
<span id="CNN"></span>
==CNNs==
As mentioned by [[Ilya Sutskever]] and [[Vinod Nair]] in 2008 <ref>[[Ilya Sutskever]], [[Vinod Nair]] ('''2008'''). ''Mimicking Go Experts with Convolutional Neural Networks''. [http://dblp.uni-trier.de/db/conf/icann/icann2008-2.html#SutskeverN08 ICANN 2008], [http://www.cs.utoronto.ca/~ilya/pubs/2008/go_paper.pdf pdf]</ref>, [[Neural Networks#Convolutional|convolutional neural networks]] are well suited for problems with a [https://en.wikipedia.org/wiki/Translational_symmetry natural translation invariance], such as [https://en.wikipedia.org/wiki/Outline_of_object_recognition object recognition]. Go has some translation invariance, because if all the pieces on a hypothetical Go board are shifted to the left, then the best move will also shift (with the exception of pieces that are on the boundary of the board). Many applications of neural networks to Go have already used convolutional neural networks, such as [[Nicol N. Schraudolph]] et al. <ref>[[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''19941993'''). ''[httphttps://nicpapers.schraudolphnips.orgcc/bib2htmlpaper/b2hd820-temporal-difference-learning-of-position-evaluation-in-the-SchDaySej94.html game-of-go Temporal Difference Learning of Position Evaluation in the Game of Go]''. [httphttps://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6NIPS 1993]</ref>, [[Erik van der Werf]] et al. <ref>[[Erik van der Werf]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007%2F978-3-540-40031-8_26 Local Move Prediction in Go]''. [[CG 2002]]</ref>, and [[Markus Enzenberger]] <ref>[[Markus Enzenberger]] ('''2003'''). ''[http://webdocs.cs.ualberta.ca/~emarkus/neurogo/neurogo3/index.html Evaluation in Go by a Neural Network using Soft Segmentation]''. [[Advances in Computer Games 10]], [http://webdocs.cs.ualberta.ca/~emarkus/publications/neurogo3.pdf pdf]</ref>, among others.
In 2014, two teams independently investigated whether deep convolutional neural networks <ref>[https://en.wikipedia.org/wiki/Convolutional_neural_network Convolutional neural network from Wikipedia]</ref> could be used to directly represent and [[Learning|learn]] a move evaluation function for the game of Go. [[Christopher Clark]] and [[Amos Storkey]] trained an 8-layer convolutional neural network by [[Supervised Learning|supervised learning]] from a database of human professional games, which without any [[Search|search]], defeated the traditional search program [[Gnu Go]] in 86% of the games <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://erikbern.com/2014/12/11/deep-learning-for-go/ Deep learning for… Go] by [[Erik Bernhardsson]], December 11, 2014</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://www.technologyreview.com/view/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>. In their 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]] report they trained a large 12-layer convolutional neural network in a similar way, to beat Gnu Go in 97% of the 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>.
* [[David Fotland]] ('''1993'''). ''[http://www.smart-games.com/knowpap.txt Knowledge representation in the Many Faces of Go]''.
* [[Bernd Brügmann]] ('''1993'''). ''Monte Carlo Go''. [http://www.ideanest.com/vegos/MonteCarloGo.pdf pdf] <ref>[http://www.cgl.ucsf.edu/home/pett/go/Programs/Gobble.html Gobble]</ref>
* [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''1993'''). ''[https://papers.nips.cc/paper/820-temporal-difference-learning-of-position-evaluation-in-the-game-of-go Temporal Difference Learning of Position Evaluation in the Game of Go]''. [https://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 NIPS 1993] <ref>[http://satirist.org/learn-game/systems/go-net.html Nici Schraudolph’s go networks], review by [[Jay Scott]]</ref>
'''1994'''
* [[Elwyn Berlekamp]], [[David Wolfe]] ('''1994'''). ''[https://math.berkeley.edu/~berlek/cgt/gobook.html Mathematical Go - Chilling Gets the Last Point]''. [https://en.wikipedia.org/wiki/A_K_Peters,_Ltd. A K Peters Ltd.], also in paperback as ''Mathematical Go Endgames: Nightmares For the Professional Go Player''. [https://en.wikipedia.org/wiki/Ishi_Press Ishi Press] <ref>[http://senseis.xmp.net/?MathematicalGo Mathematical Go] from [http://senseis.xmp.net/?About Sensei's Library]</ref>
==1995 ...==
* <span id="CSTR339"></span>[[Jay Burmeister]], [[Janet Wiles]] ('''1995'''). ''[http://staff.itee.uq.edu.au/janetw/Computer%20Go/CS-TR-339.html CS-TR-339 Computer Go Tech Report]''. Departments of Computer Science and Psychology, [https://en.wikipedia.org/wiki/University_of_Queensland The University of Queensland], [https://en.wikipedia.org/wiki/St_Lucia,_Queensland QLD 4072], [https://en.wikipedia.org/wiki/Australia Australia] (permanently - under construction)
* [[Bruno Bouzy]] ('''2001'''). ''Go Patterns Generated by Retrograde Analysis''. [[6th Computer Olympiad#Workshop|6th Computer Olympiad Workshop]], [http://www.mi.parisdescartes.fr/~bouzy/publications/RAGO.pdf pdf]
* [[Erik van der Werf]], [[Jaap van den Herik]] ('''2001'''). ''Visual Learning in Go''. [[6th Computer Olympiad#Workshop|6th Computer Olympiad Workshop]], [http://erikvanderwerf.tengen.nl/pubdown/visual_learning_in_go.pdf pdf]
* [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''2001'''). ''[http://nic.schraudolph.org/bib2html/b2hd-SchDaySej01.html Learning to Evaluate Go Positions via Temporal Difference Methods]''. in [[Norio Baba]], [[Lakhmi C. Jain]] (eds.) ('''2001'''). ''[http://jasss.soc.surrey.ac.uk/7/1/reviews/takama.html Computational Intelligence in Games, Studies in Fuzziness and Soft Computing]''. , [http://www.springer.com/economics?SGWID=1-165-6-73481-0 Physica-Verlag], revised version of [[Nicol N. Schraudolph#19941993|1994 1993 paper]]
* [[Tristan Cazenave]] ('''2001'''). ''Generating Patterns with External Conditions for the Game of Go''. [[Advances in Computer Games 9]], [http://www.lamsade.dauphine.fr/~cazenave/papers/acg9-final.pdf pdf]
* [[Jeng-Chi Yan]], [[Shun-Chin Hsu]] ('''2001'''). ''A Positional Judgment System for computer Go''. [[Advances in Computer Games 9]]
