25,161
edits
Changes
Created page with "'''Home * Search * Move Ordering * Neural MoveMap Heuristic''' FILE:Single layer ann.svg|border|right|thumb|Feedforward artificial neural network <ref..."
'''[[Main Page|Home]] * [[Search]] * [[Move Ordering]] * Neural MoveMap Heuristic'''
[[FILE:Single layer ann.svg|border|right|thumb|Feedforward artificial neural network <ref>Depiction of a single-layer feedforward artificial neural network. Arrows originating at x2 are omitted for clairty. This network has p inputs and q outputs. [https://commons.wikimedia.org/wiki/File:Single_layer_ann.svg Image] by [https://en.wikipedia.org/wiki/User:Mcstrother Mcstrother], February 17, 2010, [https://creativecommons.org/licenses/by/3.0/deed.en CC BY 3.0], [https://en.wikipedia.org/wiki/Wikimedia_Commons Wikimedia Commons], [https://en.wikipedia.org/wiki/Artificial_neural_network Artificial neural network from Wikipedia]</ref> ]]
'''Neural MoveMap Heuristic''', (NMM heuristic)<br/>
a move ordering heuristic introduced by [[Levente Kocsis]] at al., applied to the games of [[Lines of Action]] <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2001'''). ''Move Ordering using Neural Networks''. IEA/AIE 2001, [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNCS] 2070</ref> and chess <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]</ref>. The NMM heuristic utilizes a [[Neural Networks|neural network]], trained to estimate the likelihood of a [[Moves|move]] being the [[Best Move|best one]] in a certain [[Chess Position|chess position]]. The best performing NN architecture resulted from an input layer consisting of 6 neurons per [[Squares|square]] (for each particular [[Pieces|piece]], -1 Black, 0-None, +1 White) plus one neuron for the side to move, and an [[Butterfly Boards|butterfly]] output layer of 1792 neurons corresponding to valid 64x64 [[Origin Square|from-]] and [[Target Square|to-squares]] of the moves. Although the network is very large, the move scores can be computed quickly, since one only has to propagate the activation for the pieces actually on the board, and to compute only the scores for the legal moves. An enhanced approach of the NMM heuristic used a weighted combination of the neural network and the [[History Heuristic|history-heuristic]] scores, tested for middle-game chess positions with [[Crafty]], yielding in encouraging results using [https://en.wikipedia.org/wiki/Rprop Rprop] as [[Learning|learning]] [[Algorithms|algorithm]] during the training phase with 4 times (from [[ECO]] A30, B84, D85 and E97) 3000 positions <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]</ref>.
=See also=
* [[Butterfly Boards]]
* [[Chessmaps Heuristic]]
* [[Guard Heuristic]]
* [[History Heuristic]]
* [[Neural Networks]]
* [[Temporal Difference Learning]]
=Publications=
* [[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2001'''). ''Move Ordering using Neural Networks''. IEA/AIE 2001, [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNCS] 2070
* [[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]
* [[Mark Winands]], [[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2002'''). ''Temporal difference learning and the Neural MoveMap heuristic in the game of Lines of Action''. GAME-ON 2002
* [[Levente Kocsis]] ('''2003'''). ''Learning Search Decisions''. Ph.D thesis, [[Maastricht University]], [https://project.dke.maastrichtuniversity.nl/games/files/phd/Kocsis_thesis.pdf pdf]
=External Links=
* [https://en.wikipedia.org/wiki/Backpropagation Backpropagation from Wikipedia]
* [https://en.wikipedia.org/wiki/Feedforward_neural_network Feedforward neural network from Wikipedia]
* [https://en.wikipedia.org/wiki/Rprop Rprop from Wikipedia]
* [https://en.wikipedia.org/wiki/Brecker_Brothers Brecker Brothers] - Sponge, [https://sv.wikipedia.org/wiki/Kristianstad/%C3%85hus_Jazzfestival Kristianstad/Åhus Jazzfestivalen], July 1980, [https://en.wikipedia.org/wiki/YouTube YouTube] Video
: [[Videos#MichaelBrecker|Michael Brecker]], [[Videos#RandyBrecker|Randy Brecker]], [https://en.wikipedia.org/wiki/Barry_Finnerty Barry Finnerty], [http://www.allmusic.com/artist/mark-gray-mn0001423900/credits Mark Gray], [https://en.wikipedia.org/wiki/Neil_Jason Neil Jason], [http://www.allmusic.com/artist/richie-morales-mn0000298182/credits Richie Morales]
: {{#evu:https://www.youtube.com/watch?v=NeGbOmmxGck|alignment=left|valignment=top}}
=References=
<references />
'''[[Move Ordering|Up one Level]]'''
[[FILE:Single layer ann.svg|border|right|thumb|Feedforward artificial neural network <ref>Depiction of a single-layer feedforward artificial neural network. Arrows originating at x2 are omitted for clairty. This network has p inputs and q outputs. [https://commons.wikimedia.org/wiki/File:Single_layer_ann.svg Image] by [https://en.wikipedia.org/wiki/User:Mcstrother Mcstrother], February 17, 2010, [https://creativecommons.org/licenses/by/3.0/deed.en CC BY 3.0], [https://en.wikipedia.org/wiki/Wikimedia_Commons Wikimedia Commons], [https://en.wikipedia.org/wiki/Artificial_neural_network Artificial neural network from Wikipedia]</ref> ]]
'''Neural MoveMap Heuristic''', (NMM heuristic)<br/>
a move ordering heuristic introduced by [[Levente Kocsis]] at al., applied to the games of [[Lines of Action]] <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2001'''). ''Move Ordering using Neural Networks''. IEA/AIE 2001, [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNCS] 2070</ref> and chess <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]</ref>. The NMM heuristic utilizes a [[Neural Networks|neural network]], trained to estimate the likelihood of a [[Moves|move]] being the [[Best Move|best one]] in a certain [[Chess Position|chess position]]. The best performing NN architecture resulted from an input layer consisting of 6 neurons per [[Squares|square]] (for each particular [[Pieces|piece]], -1 Black, 0-None, +1 White) plus one neuron for the side to move, and an [[Butterfly Boards|butterfly]] output layer of 1792 neurons corresponding to valid 64x64 [[Origin Square|from-]] and [[Target Square|to-squares]] of the moves. Although the network is very large, the move scores can be computed quickly, since one only has to propagate the activation for the pieces actually on the board, and to compute only the scores for the legal moves. An enhanced approach of the NMM heuristic used a weighted combination of the neural network and the [[History Heuristic|history-heuristic]] scores, tested for middle-game chess positions with [[Crafty]], yielding in encouraging results using [https://en.wikipedia.org/wiki/Rprop Rprop] as [[Learning|learning]] [[Algorithms|algorithm]] during the training phase with 4 times (from [[ECO]] A30, B84, D85 and E97) 3000 positions <ref>[[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]</ref>.
=See also=
* [[Butterfly Boards]]
* [[Chessmaps Heuristic]]
* [[Guard Heuristic]]
* [[History Heuristic]]
* [[Neural Networks]]
* [[Temporal Difference Learning]]
=Publications=
* [[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2001'''). ''Move Ordering using Neural Networks''. IEA/AIE 2001, [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNCS] 2070
* [[Levente Kocsis]], [[Jos Uiterwijk]], [[Eric Postma]], [[Jaap van den Herik]] ('''2002'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-40031-8_11 The Neural MoveMap Heuristic in Chess]''. [[CG 2002]], [http://www.pradu.us/old/Nov27_2008/Buzz/research/parallel/movemap_heuristic.pdf pdf]
* [[Mark Winands]], [[Levente Kocsis]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2002'''). ''Temporal difference learning and the Neural MoveMap heuristic in the game of Lines of Action''. GAME-ON 2002
* [[Levente Kocsis]] ('''2003'''). ''Learning Search Decisions''. Ph.D thesis, [[Maastricht University]], [https://project.dke.maastrichtuniversity.nl/games/files/phd/Kocsis_thesis.pdf pdf]
=External Links=
* [https://en.wikipedia.org/wiki/Backpropagation Backpropagation from Wikipedia]
* [https://en.wikipedia.org/wiki/Feedforward_neural_network Feedforward neural network from Wikipedia]
* [https://en.wikipedia.org/wiki/Rprop Rprop from Wikipedia]
* [https://en.wikipedia.org/wiki/Brecker_Brothers Brecker Brothers] - Sponge, [https://sv.wikipedia.org/wiki/Kristianstad/%C3%85hus_Jazzfestival Kristianstad/Åhus Jazzfestivalen], July 1980, [https://en.wikipedia.org/wiki/YouTube YouTube] Video
: [[Videos#MichaelBrecker|Michael Brecker]], [[Videos#RandyBrecker|Randy Brecker]], [https://en.wikipedia.org/wiki/Barry_Finnerty Barry Finnerty], [http://www.allmusic.com/artist/mark-gray-mn0001423900/credits Mark Gray], [https://en.wikipedia.org/wiki/Neil_Jason Neil Jason], [http://www.allmusic.com/artist/richie-morales-mn0000298182/credits Richie Morales]
: {{#evu:https://www.youtube.com/watch?v=NeGbOmmxGck|alignment=left|valignment=top}}
=References=
<references />
'''[[Move Ordering|Up one Level]]'''
