I am interested in statistical machine learning and biologically-inspired computer vision, with an emphasis on unsupervised learning and time series analysis.

I completed my PhD at the University of Toronto in 2009. My PhD thesis was titled "Composable, distributed-state models for high-dimensional time series". My thesis co-advisors were Geoffrey Hinton and Sam Roweis. I did a postdoc at NYU with Chris Bregler, Rob Fergus, and Yann LeCun.

I am looking for Master's and PhD students who are interested in Deep Learning and Representation Learning. If you are interested in working with me, you will need to apply to the Engineering Systems and Computing graduate program (School of Engineering).

"Mental Rotation" by Optimizing Transforming Distance
Weiguang Ding and Graham W. Taylor (2014)
ArXiv preprint.

Multi-scale deep learning for gesture detection and localization
Natalia Neverova, Christian Wolf, Graham W. Taylor and Florian Nebout (2014)
ECCV ChaLearn Workshop on Looking at People, 2014.
This paper describes the winning entry of the ChaLearn 2014 gesture recognition competition. Results

Learning Human Pose Estimation Features with Convolutional Networks
Arjun Jain, Jonathan Tompson, Mykhaylo Andriluka, Graham W. Taylor and Christoph Bregler (2014)
International Conference on Learning Representations (ICLR)