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

Terry Bossomaier, James Traish, Fernand Gobet, Peter Lane

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)


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 localglobal
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
Original languageEnglish
Title of host publicationInternational Joint Conference on Neural Networks (IJCNN 2012)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)978-1-4673-1489-3
ISBN (Print)978-1-4673-1488-6
Publication statusPublished - 2012


Dive into the research topics of 'Neuro-cognitive model of move location in the game of Go'. Together they form a unique fingerprint.

Cite this