I am interested in Machine Learning, specifically in studying graphical models for complex time series data.

I recently finished a PhD at the University of Toronto. My PhD thesis was titled "Composable, distributed-state models for high-dimensional time-series". My thesis co-advisors were Geoffrey Hinton and Sam Roweis.

At NYU my faculty collaborators are Chris Bregler, Rob Fergus, and Yann LeCun.

Modeling Human Motion Using Binary Latent Variables
Supplementary Material (including videos and source code)
Graham Taylor, Geoffrey Hinton, and Sam Roweis (2007)
Proc. of Advances in Neural Information Processing Systems (NIPS) 19

Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style
Supplementary Material (including videos)
Graham Taylor and Geoffrey Hinton (2009)
Proc. of the 26th International Conference on Machine Learning (ICML). To appear.

Products of Hidden Markov Models: It Takes N>1 to Tango
Graham Taylor and Geoffrey Hinton (2009)
Proc. of the 25th Conference on Uncertainty in Artificial Intelligence (UAI). To appear.