Title :
A hybrid Artificial Intelligence approach with application to games
Author :
Cant, Richard ; Churchill, Julian ; Al-Dabass, David
Author_Institution :
Dept. of Comput. & Math., Nottingham Trent Univ., UK
fDate :
6/24/1905 12:00:00 AM
Abstract :
We describe a hybrid Artificial Intelligence (AI) approach combining soft AI techniques (neural networks) and hard AI methods (alpha-beta game tree search), in an attempt to approximate human play more accurately, in particular with reference to the game of Go. The program is tested and analysed by play against another Go playing program and it is shown that the use of hard AI enhances the performance of the soft AI system and vice-versa
Keywords :
artificial intelligence; feedforward neural nets; game theory; tree searching; alpha-beta game tree search; game of Go; hard AI methods; hybrid artificial intelligence approach; neural networks; soft AI techniques; Artificial intelligence; Artificial neural networks; Biological neural networks; Biological system modeling; Brain modeling; Computer networks; Humans; Neural networks; Neurons; Search methods;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007752
