Volodymyr Mnih

Department of Computer Science University of Toronto Toronto, Ontario Email: vmnih at cs dot toronto dot edu

About Me

I'm a research scientist at Google DeepMind. I completed a PhD in Machine Learning at the University of Toronto working under the supervision of Geoffrey Hinton. Before that, I completed a Master's degree in computing science at the University of Alberta where I was supervised by Csaba Szepesvari.

Publications

• Human-level Control through Deep Reinforcement Learning [Code] [BibTeX]
  Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis.
  In Nature, 518: 529–533, 2015.
• Multiple Object Recognition with Visual Attention [PDF] [BibTeX]
  Jimmy Ba, Volodymyr Mnih, Koray Kavukcuoglu
  ICLR, 2015.
• Recurrent Models of Visual Attention [PDF] [Datasets] [BibTeX]
  Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu
  In Advances in Neural Information Processing Systems, 2014.
• Playing Atari With Deep Reinforcement Learning [PDF] [BibTeX]
  Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller
  NIPS Deep Learning Workshop, 2013.
• Machine Learning for Aerial Image Labeling [PDF] [Datasets] [BibTeX]
  Volodymyr Mnih
  PhD Thesis, University of Toronto, 2013.
• Modeling Natural Images Using Gated MRFs [PDF] [BibTeX]
  Marc'Aurelio Ranzato, Volodymyr Mnih, Joshua Susskind, Geoffrey Hinton
  In IEEE Trans. Pattern Analysis and Machine Intelligence, 2013.
• Learning to Label Aerial Images from Noisy Data [PDF] [BibTeX]
  Volodymyr Mnih and Geoffrey Hinton
  In Proceedings of the 29th International Conference on Machine Learning, 2012.
• Conditional Restricted Boltzmann Machines for Structured Output Prediction. [PDF] [BibTeX]
  Volodymyr Mnih, Hugo Larochelle and Geoffrey Hinton
  In Proc. of The 27th Conference on Uncertainty in Artificial Intelligence, 2011.
• On Deep Generative Models with Applications to Recognition. [PDF] [BibTeX]
  Marc'Aurelio Ranzato, Joshua Susskind, Volodymyr Mnih, Geoffrey Hinton
  In Proc. of Computer Vision and Pattern Recognition Conference, 2011.
• How to generate realistic images using gated MRFs. [PDF] [BibTeX]
  Marc'Aurelio Ranzato, Volodymyr Mnih, Geoffrey Hinton
  In Advances in Neural Information Processing Systems 23, 2010.
• Learning to Detect Roads in High-Resolution Aerial Images. [PDF] [BibTeX]
  Volodymyr Mnih and Geoffrey Hinton
  European Conference on Computer Vision, 2010.
• CUDAMat: A CUDA-based matrix class for Python. [PDF] [BibTeX]
  Volodymyr Mnih
  UTML TR 2009-004.
• Efficient Stopping Rules [PDF]
  Volodymyr Mnih
  Master's Thesis, University of Alberta, 2008.
• Empirical Bernstein Stopping [PDF] [BibTeX]
  Volodymyr Mnih, Csaba Szepesvari, Jean-Yves Audibert
  In Proceedings of the 25th International Conference on Machine Learning, 2008.
• Topological Map Learning from Outdoor Image Sequences [PDF]
  Xuming He, Richard Zemel, Volodymyr Mnih
  In Journal of Field Robotics, 23: 1091-1104, 2006.
• Memview: A Pedagogically-Motivated Visual Debugger
  Paul Gries, Volodymyr Mnih, Jonathan Taylor, Greg Wilson, and Lee Zamparo
  In ASEE/IEEE Frontiers in Education, 2005.