2003
Learning Representative Patterns From Real Chess Positions: A Case Study
ŽIŽKA, Jan a Michal MÁDRZákladní údaje
Originální název
Learning Representative Patterns From Real Chess Positions: A Case Study
Autoři
ŽIŽKA, Jan a Michal MÁDR
Vydání
Hyderabad, India, Proceedings of the First Indian International Conference on Artificial Intelligence (IICAI-03), od s. 1374-1387, 14 s. 2003
Nakladatel
IICAI-03
Další údaje
Jazyk
angličtina
Typ výsledku
Stať ve sborníku
Obor
10201 Computer sciences, information science, bioinformatics
Stát vydavatele
Indie
Utajení
není předmětem státního či obchodního tajemství
Označené pro přenos do RIV
Ano
Kód RIV
RIV/00216224:14330/03:00009152
Organizační jednotka
Fakulta informatiky
ISBN
0-9727412-0-8
Klíčová slova anglicky
pattern recognition; decision trees; classification; representation of examples; relevant attributes
Štítky
Změněno: 8. 9. 2004 16:36, doc. Ing. Jan Žižka, CSc.
Anotace
V originále
This paper deals with a particular pattern recognition by machine learning. The patterns are specific chess positions. A computer learns if a special pattern leads to a winning or losing game, i.e., a classification task based on real results and examples. As a learning algorithm, decision trees generated by the program C5/See5, also with boosting, were used. This algorithm does not employ chess rules or calculations of positions, it just learns from a selected set of 450 training positive and negative examples with 8 different representations of real positions played by human players. The most accurate classification reaches 92.98% for the combination of automatically generated trivial descriptions of positions (64 attributes) with expert descriptions suggested by humans (92 attributes).
Návaznosti
| MSM 143300003, záměr |
|