Abstract
In May 2017, the application of deep learning to the game “Go” enjoyed a tremendous victory when the AlphaGo computer program beat one of the top professional players. However, there is no clear understanding of why deep learning elicits such strong performance. In this paper, we introduce visualization techniques used in image recognition to investigate the functions of the intermediate layers and operations of the Go policy network. Used as a diagnostic tool, these visualization techniques allow us to understand what happens during the training of policy networks. We also introduce a visualization technique that performs a sensitivity analysis of the classifier output by occluding portions of the input Go board, revealing which parts of the board are important for predicting the next move.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Clark, C., Storkey, A.: Training deep convolutional neural networks to play go. In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), pp. 1766–1774 (2015)
Tian, Y., Zhu, Y.: Better computer go player with neural network and long-term prediction. arXiv preprint arXiv:1511.06410 (2015)
Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Maddison, C.J., et al.: Move evaluation in go using deep convolutional neural networks. arXiv preprint arXiv:1412.6564 (2014)
Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354–359 (2017)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
GoGoD. https://gogodonline.co.uk
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Pang, Y., Ito, T. (2018). Visualizing and Understanding Policy Networks of Computer Go. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11012. Springer, Cham. https://doi.org/10.1007/978-3-319-97304-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-97304-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97303-6
Online ISBN: 978-3-319-97304-3
eBook Packages: Computer ScienceComputer Science (R0)