DocumentCode :
1648781
Title :
Modeling and verification of the "cause &effect" relation comprehension by neural networks using learning algorithms
Author :
Muquit, M.A. ; Sawada, Yasuji
Author_Institution :
Graduate Sch. of Inf. Sci., Tohoku Univ., Sendai, Japan
Volume :
1
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
939
Lastpage :
943
Abstract :
The capability of predicting what will happen next based on past experiences and environment features could be thought of as one kind of cause & effect comprehension. We have modeled a system to attain this capability by neural networks using reinforcement and supervised learning algorithms to comprehend the ground shot in a golf game. The system predicts the approximate distance the golf ball runs and we have found that the system works very well and it becomes almost perfect just after practicing with several samples
Keywords :
learning (artificial intelligence); neural nets; bias knowledge; cause and effect relation comprehension; ground shot; learning algorithms; neural networks; prediction; reinforcement learning; supervised learning; Biological neural networks; Biology computing; Humans; Information science; Machine learning; Neural networks; Prediction algorithms; Predictive models; Supervised learning; Watches;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
ISSN :
1098-7576
Print_ISBN :
0-7803-7278-6
Type :
conf
DOI :
10.1109/IJCNN.2002.1005601
Filename :
1005601
Link To Document :
بازگشت