Title :
Trained neural networks play chess endgames
Author :
Si, Jie ; Tang, FZilun
Author_Institution :
Comsearch, Reston, VA, USA
Abstract :
In this paper, three types of chess endgames were studied and three layer feedforward neural networks were applied to learn the hidden rules in chess endgames. The purpose of this paper is to convert the symbolic rules of chess endgames into numerical information that neural networks can learn. The neural networks have been proved efficient in learning and playing some simple cases of chess endgames
Keywords :
feedforward neural nets; games of skill; learning (artificial intelligence); multilayer perceptrons; chess endgames; hidden rule learning; symbolic rules; three layer feedforward neural networks; trained neural networks; Biological neural networks; Feedforward neural networks; Humans; IEEE members; Intelligent networks; Intelligent robots; Mathematical model; Neural networks; Pattern recognition; Signal processing;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.830745
