Authors
Chris J Maddison, Aja Huang, Ilya Sutskever, David Silver
Publication date
2015
Journal
International Conference on Learning Representations
Description
Abstract: The game of Go is more challenging than other board games, due to the difficulty of
constructing a position or move evaluation function. In this paper we investigate whether
deep convolutional networks can be used to directly represent and learn this knowledge. We
train a large 12-layer convolutional neural network by supervised learning from a database
of human professional games. The network correctly predicts the expert move in 55% of
positions, equalling the accuracy of a 6 dan human player. When the trained convolutional ...
constructing a position or move evaluation function. In this paper we investigate whether
deep convolutional networks can be used to directly represent and learn this knowledge. We
train a large 12-layer convolutional neural network by supervised learning from a database
of human professional games. The network correctly predicts the expert move in 55% of
positions, equalling the accuracy of a 6 dan human player. When the trained convolutional ...
Total citations
Scholar articles
CJ Maddison, A Huang, I Sutskever, D Silver - arXiv preprint arXiv:1412.6564, 2014
Dates and citation counts are estimated and are determined automatically by a computer program.