25,161
edits
Changes
Created page with "'''Home * Engines * Tempo (engine)''' [[FILE:Dragon trees.jpg|border|right|thumb| [https://en.wikipedia.org/wiki/Fractal Fractal] [https://en.wikipedia.org/..."
'''[[Main Page|Home]] * [[Engines]] * Tempo (engine)'''
[[FILE:Dragon trees.jpg|border|right|thumb| [https://en.wikipedia.org/wiki/Fractal Fractal] [https://en.wikipedia.org/wiki/Tree Trees] using [https://en.wikipedia.org/wiki/L-system L-system] <ref>cropped from [https://commons.wikimedia.org/wiki/File:Dragon_trees.jpg Fractal trees] by [https://commons.wikimedia.org/wiki/Template:Solkoll Solkoll]. The images of the trees was generated from using a [https://en.wikipedia.org/wiki/L-system L-system]. The [https://commons.wikimedia.org/wiki/Fractal fractal] used is a varied [https://en.wikipedia.org/wiki/Dragon_curve dragon curve], [https://en.wikipedia.org/wiki/Wikimedia_Commons Wikimedia Commons], [https://en.wikipedia.org/wiki/L-system L-system from Wikipedia]</ref> ]]
'''Tempo''',<br/>
an experimental chess engine developed by [[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], and [[François Scharffe]], using an [[Neural Networks|artificial neuronal network]] as [[Evaluation Function|evaluation function]] generated by a [[Genetic Programming#GeneticAlgorithm|genetic algorithm]]. Tempo applies [https://en.wikipedia.org/wiki/L-system L-systems] as elaborated by [[Egbert Boers]] and [[Herman Kuiper]] <ref>[[Egbert Boers]], [[Herman Kuiper]] ('''1992'''). ''Biological metaphors and the design of modular artificial neural networks''. Master’s thesis, [[Leiden University]], [http://liacs.leidenuniv.nl/assets/PDF/boers-kuiper.92.pdf pdf]</ref>, to generate [https://en.wikipedia.org/wiki/Modular_neural_network modular neural networks] whose size is independent of that of the [https://en.wikipedia.org/wiki/Chromosome_%28genetic_algorithm%29 chromosome] and [https://en.wikipedia.org/wiki/Crossover_%28genetic_algorithm%29 crossover] tolerant. A population of L-system construction rules is generated to mark the resulting networks according to their capabilities to [[Learning|learn]] game position evaluations from real games. Simple aspects were learnt at first. Strongest individuals learnt more complex faetures, from [[Material|material]] to [[Square Control|square control]] and [[Pawn Structure|pawn structure]] <ref>[[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], [[François Scharffe]] ('''2004'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-24650-3_1 Evaluation of Chess Position by Modular Neural network Generated by Genetic Algorithm]''. [http://www.informatik.uni-trier.de/~ley/db/conf/eurogp/eurogp2004.html#AutonesBCLLS04 EuroGP 2004]</ref>.
=See also=
* [[Neural Networks#engines|Chess Engines with Neural Networks]]
* [[Learning#Programs|Learning Chess Programs]]
* [[Tempo]]
=Publications=
* [[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], [[François Scharffe]] ('''2004'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-24650-3_1 Evaluation of Chess Position by Modular Neural network Generated by Genetic Algorithm]''. [http://www.informatik.uni-trier.de/~ley/db/conf/eurogp/eurogp2004.html#AutonesBCLLS04 EuroGP 2004]
=Abstract=
{| class="wikitable"
|-
| In this article we present our chess engine Tempo. One of the major difficulties for this type of program lies in the function for evaluating game positions. This function is composed of a large number of parameters which have to be determined and then adjusted. We propose an alternative which consists in replacing this function by an artificial neuron network (ANN). Without topological knowledge of this complex network, we use the evolutionist methods for its inception, thus enabling us to obtain, among other things, a modular network. Finally, we present our results:
* Reproduction of the [[Combinatorial Logic#XOR|XOR function]] which [[Neural Networks#AIWinter|validates]] the method used
* Generation of an evaluation function
|}
=Forum Posts=
* [https://www.stmintz.com/ccc/index.php?id=358770 Presentation for a neural net learning chess program] by [[Dann Corbit]], [[CCC]], April 06, 2004
=External Links=
* [https://en.wikipedia.org/wiki/Tempo Tempo from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28disambiguation%29 Tempo (disambiguation) from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28chess%29 Tempo (chess) from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28app%29 Tempo (app) from Wikipedia]
* [[:Category:Yamandu Costa|Yamandu Costa]] - [http://www.allmusic.com/album/tempo-feliz-mw0000952642 Tempo Feliz] ([https://en.wikipedia.org/wiki/Baden_Powell_de_Aquino Baden Powell]), [http://www.yamandu.com.br/music.php?cod=8 Tokyo Session] (2006), [https://en.wikipedia.org/wiki/YouTube YouTube] Video
: {{#evu:https://www.youtube.com/watch?v=FCRJEyOsIsY|alignment=left|valignment=top}}
=References=
<references />
'''[[Engines|Up one Level]]'''
[[Category:Yamandu Costa]]
[[FILE:Dragon trees.jpg|border|right|thumb| [https://en.wikipedia.org/wiki/Fractal Fractal] [https://en.wikipedia.org/wiki/Tree Trees] using [https://en.wikipedia.org/wiki/L-system L-system] <ref>cropped from [https://commons.wikimedia.org/wiki/File:Dragon_trees.jpg Fractal trees] by [https://commons.wikimedia.org/wiki/Template:Solkoll Solkoll]. The images of the trees was generated from using a [https://en.wikipedia.org/wiki/L-system L-system]. The [https://commons.wikimedia.org/wiki/Fractal fractal] used is a varied [https://en.wikipedia.org/wiki/Dragon_curve dragon curve], [https://en.wikipedia.org/wiki/Wikimedia_Commons Wikimedia Commons], [https://en.wikipedia.org/wiki/L-system L-system from Wikipedia]</ref> ]]
'''Tempo''',<br/>
an experimental chess engine developed by [[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], and [[François Scharffe]], using an [[Neural Networks|artificial neuronal network]] as [[Evaluation Function|evaluation function]] generated by a [[Genetic Programming#GeneticAlgorithm|genetic algorithm]]. Tempo applies [https://en.wikipedia.org/wiki/L-system L-systems] as elaborated by [[Egbert Boers]] and [[Herman Kuiper]] <ref>[[Egbert Boers]], [[Herman Kuiper]] ('''1992'''). ''Biological metaphors and the design of modular artificial neural networks''. Master’s thesis, [[Leiden University]], [http://liacs.leidenuniv.nl/assets/PDF/boers-kuiper.92.pdf pdf]</ref>, to generate [https://en.wikipedia.org/wiki/Modular_neural_network modular neural networks] whose size is independent of that of the [https://en.wikipedia.org/wiki/Chromosome_%28genetic_algorithm%29 chromosome] and [https://en.wikipedia.org/wiki/Crossover_%28genetic_algorithm%29 crossover] tolerant. A population of L-system construction rules is generated to mark the resulting networks according to their capabilities to [[Learning|learn]] game position evaluations from real games. Simple aspects were learnt at first. Strongest individuals learnt more complex faetures, from [[Material|material]] to [[Square Control|square control]] and [[Pawn Structure|pawn structure]] <ref>[[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], [[François Scharffe]] ('''2004'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-24650-3_1 Evaluation of Chess Position by Modular Neural network Generated by Genetic Algorithm]''. [http://www.informatik.uni-trier.de/~ley/db/conf/eurogp/eurogp2004.html#AutonesBCLLS04 EuroGP 2004]</ref>.
=See also=
* [[Neural Networks#engines|Chess Engines with Neural Networks]]
* [[Learning#Programs|Learning Chess Programs]]
* [[Tempo]]
=Publications=
* [[Mathieu Autonès]], [[Aryel Beck]], [[Phillippe Camacho]], [[Nicolas Lassabe]], [[Hervé Luga]], [[François Scharffe]] ('''2004'''). ''[http://link.springer.com/chapter/10.1007/978-3-540-24650-3_1 Evaluation of Chess Position by Modular Neural network Generated by Genetic Algorithm]''. [http://www.informatik.uni-trier.de/~ley/db/conf/eurogp/eurogp2004.html#AutonesBCLLS04 EuroGP 2004]
=Abstract=
{| class="wikitable"
|-
| In this article we present our chess engine Tempo. One of the major difficulties for this type of program lies in the function for evaluating game positions. This function is composed of a large number of parameters which have to be determined and then adjusted. We propose an alternative which consists in replacing this function by an artificial neuron network (ANN). Without topological knowledge of this complex network, we use the evolutionist methods for its inception, thus enabling us to obtain, among other things, a modular network. Finally, we present our results:
* Reproduction of the [[Combinatorial Logic#XOR|XOR function]] which [[Neural Networks#AIWinter|validates]] the method used
* Generation of an evaluation function
|}
=Forum Posts=
* [https://www.stmintz.com/ccc/index.php?id=358770 Presentation for a neural net learning chess program] by [[Dann Corbit]], [[CCC]], April 06, 2004
=External Links=
* [https://en.wikipedia.org/wiki/Tempo Tempo from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28disambiguation%29 Tempo (disambiguation) from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28chess%29 Tempo (chess) from Wikipedia]
* [https://en.wikipedia.org/wiki/Tempo_%28app%29 Tempo (app) from Wikipedia]
* [[:Category:Yamandu Costa|Yamandu Costa]] - [http://www.allmusic.com/album/tempo-feliz-mw0000952642 Tempo Feliz] ([https://en.wikipedia.org/wiki/Baden_Powell_de_Aquino Baden Powell]), [http://www.yamandu.com.br/music.php?cod=8 Tokyo Session] (2006), [https://en.wikipedia.org/wiki/YouTube YouTube] Video
: {{#evu:https://www.youtube.com/watch?v=FCRJEyOsIsY|alignment=left|valignment=top}}
=References=
<references />
'''[[Engines|Up one Level]]'''
[[Category:Yamandu Costa]]
