Publications

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)

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)

Modeling Pigeon Behaviour Using a Conditional Restricted Boltzmann Machine
Matthew Zeiler, Graham Taylor, Niko Troje and Geoffrey Hinton (2009)
17th European Symposium on Artificial Neural Networks (ESANN)

The Recurrent Temporal Restricted Boltzmann Machine
Ilya Sutskever, Geoffrey Hinton, and Graham Taylor (2009)
Proc. of Advances in Neural Information Processing Systems (NIPS) 21

Deep Generative Models for Modeling Animate Motion (Extended abstract)
Graham Taylor, Geoffrey Hinton, and Sam Roweis (2008)
Proc. 4th International Symposium on Adaptive Motion of Animals and Machines (AMAM)

Maximum a Posteriori ICA: Applying Prior Knowledge to the Separation of Acoustic Sources
Graham Taylor, Michael Seltzer, and Alex Acero (2008)
Proc. of the IEEE International Conference on Audio, Speech and Signal Processing (ICASSP)

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

Reinforcement Learning for Parameter Control of Text Detection in Images from Video Sequences
Graham Taylor and Christian Wolf (2004)
Proc. of the 1st International Conference on Information & Communication Technologies

A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications
Graham Taylor (2004)
Proc. of the 1st Canadian Conference on Computer and Robot Vision

Reinforced Contrast Adaptation
Hamid Tizhoosh, and Graham Taylor
International Journal of Image and Graphics 6(3): 377-392 (2006)

Hurdle Preflight in Springboard Diving: A Case of Diminishing Returns (Abstract)
Doris Miller, Alexandra Zecevic, and Graham Taylor
Research Quarterly for Exercise and Sport 73: 134-145 (2002)

Composable, distributed-state models for high-dimensional time series
Graham Taylor
PhD thesis, University of Toronto (2009)

Compact Modeling of High-Dimensional Time-Series
Graham Taylor
Depth Oral Paper, University of Toronto (2008)

Reinforcement Learning for Parameter Control of Image-Based Applications
Graham Taylor
MASc Thesis, University of Waterloo (2004)