Chris J. Maddison
I am a PhD student of machine learning at the University of Toronto supervised by Geoffrey Hinton. I was one of the primary contributors to the AlphaGo project. My research interests are probabilistic inference and Monte Carlo methods. My other interests include neural networks, learning in non-human animals, and probability theory.
- Department of Computer Science
- University of Toronto
- 6 King's College Rd.
- Toronto, Ontario
- M5S 3G4, Canada
- e-mail: cmaddis [at] cs [dot] toronto [dot] edu
- Google DeepMind announces AlphaGo. AlphaGo is the strongest Go bot to date and will challenge Lee Sedol, the strongest human player of the last decade, in March. We started the project two years ago with a small team, and today it's a big effort with an amazing group of researchers and engineers. Congratulations to everyone!
- There is now code for A* Sampling available.
Work in progress
A Poisson process model for Monte Carlo
to appear in Perturbation, Optimization, and Statistics. T. Hazan, G. Papandreou, D. Tarlow (Eds.), 2016.
Mastering the game of Go with deep neural networks and tree search
Nature, Vol. 529, 484-489, 2016
Move Evaluation in Go Using Deep Convolutional Neural Networks
International Conference on Learning Representations, 2015
[pdf] [bibtex] [sgf]
Neural Information Processing Systems, 2014
[Oral Presentation] [Best Paper Award]
[pdf] [bibtex] [supplementary] [code]
Structured Generative Models of Natural Source Code
The 31st International Conference on Machine Learning, 2014
[pdf] [bibtex] [supplementary]
Annealing Between Distributions by Averaging Moments
Neural Information Processing Systems, 2013
[pdf] [bibtex] [supplementary] [RBM weights as .npz]
Soft song during aggressive interactions: Seasonal changes and endocrine correlates in song sparrows
Hormones and Behaviour, 2012
Rapid and Widespread Effects of 17-beta-estradiol on Intracellular Signaling in the Male Songbird Brain