Library Header Image
LSE Research Online LSE Library Services

Neuro-cognitive model of move location in the game of Go

Bossomaier, Terry, Traish, Jason, Gobet, Fernand ORCID: 0000-0002-9317-6886 and Lane, Peter C.R. (2012) Neuro-cognitive model of move location in the game of Go. In: The 2012 International Joint Conference on Neural Networks (IJCNN): World Congress on Computational Intelligence. Proceedings of the International Joint Conference on Neural Networks (2012). IEEE, New York, US. ISBN 9781467314886

Full text not available from this repository.

Identification Number: 10.1109/IJCNN.2012.6252377


Although computer Go players are now better than humans on small board sizes, they are still a fair way from the top human players on standard board sizes. Thus the nature of human expertise is of great interest to artificial intelligence. Human play relies much more on pattern memory and has been extensively explored in chess. The big challenge in Go is local-global interaction - local search is good but global integration is weak. We used techniques based on the cognitive neuroscience of chess to predict optimal areas to move using perceptual chunks, which we cross-validated against game records comprising upwards of five million positions. Prediction to within a small window was about 50%, a remarkable result.

Item Type: Book Section
Official URL:
Additional Information: © 2012 IEEE
Divisions: CPNSS
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Date Deposited: 11 Dec 2019 00:56
Last Modified: 06 Jun 2024 17:06

Actions (login required)

View Item View Item