Title :
Representing evaluation of computer Chinese chess by artificial neural network using genetic algorithm
Author :
Wang, Jiao ; Sizhong
Author_Institution :
Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang
Abstract :
The evaluation is the key to computer Chinese chess, which is represented by ANN in this paper. Then, it is proposed that the connection weights of neurons of ANN can be adjusted by genetic algorithm (GA). Encoding method, fitness function, and genetic operators are given, thus the training algorithm by GA is investigated. Experiments show that the proposed algorithm performs better than back-propagation.
Keywords :
computer games; genetic algorithms; learning (artificial intelligence); neural nets; ANN; GA; artificial neural network; back propagation; computer Chinese chess; encoding method; genetic algorithm; machine leaning method; Artificial neural networks; Computer networks; Genetic algorithms; Artificial intelligence (ANN); Genetic algorithm (GA); computer Chinese chess; evaluation;
Conference_Titel :
Control and Decision Conference, 2008. CCDC 2008. Chinese
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-1733-9
Electronic_ISBN :
978-1-4244-1734-6
DOI :
10.1109/CCDC.2008.4597510
