Associate Professor
School of Engineering, University of Guelph and
Vector Institute
CIFAR Azrieli Global Scholar
Learning in Machines & Brains program
Academic Director, NextAI
Richards Building, Room 3515
I lead the Machine Learning Research Group at the University of Guelph. I am interested in statistical machine learning and biologically-inspired computer vision, with an emphasis on deep learning and time series analysis.
I received received my PhD in Computer Science from the University of Toronto in 2009, where I was advised by Geoffrey Hinton and Sam Roweis. I spent two years as a postdoc at the Courant Institute of Mathematical Sciences, New York University working with Chris Bregler, Rob Fergus, and Yann LeCun. In 2012, I joined the School of Engineering at the University of Guelph as an Assistant Professor.
A complete list of my publications is available on Google Scholar.
Terrance Devries and Graham Taylor. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017. [ bib | http ]
Devinder Kumar, Alex Wong, and Graham Taylor. Explaining the unexplained: A class-enhanced attentive response (CLEAR) approach to understanding deep neural networks. arXiv preprint arXiv:1704.04133, 2017. [ bib | http ]
Terrance Devries and Graham Taylor. Dataset augmentation in feature space. In International Conference on Learning Representations (ICLR) Workshop Track, 2017. [ bib | http ]
Dhanesh Ramachandram, Michal Lisicki, Timothy Shields, Mohamed Amer, and Graham Taylor. Structure optimization for deep multimodal fusion networks using graph-induced kernels. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2017. [ bib | .pdf ]
Fan Li, Natalia Neverova, Christian Wolf, and Graham Taylor. Modout: Learning multi-modal architectures by stochastic regularization. In 2017 IEEE Conference on Automatic Face and Gesture Recognition (FG), 2017. [ bib | .pdf ]
Matthew Veres, Medhat Moussa, and Graham Taylor. Modeling grasp motor imagery through deep conditional generative models. IEEE Robotics and Automation Letters, 2(2), 2017. [ bib | http ]
Roberto DiCecco, Griffin Lacey, Jasmina Vasiljevic, Paul Chow, Graham Taylor, and Shawki Areibi. Caffeinated FPGAs: FPGA framework for convolutional neural networks. In Field-Programmable Technology (FPT), 2016. [ bib | http ]
He Ma, Fei Mao, and Graham Taylor. Theano-MPI: a Theano-based distributed training framework. arXiv preprint arXiv:1605.08325, 2016. [ bib | http ]
Natalia Neverova, Christian Wolf, Griffin Lacey, Lex Fridman, Deepak Chandra, Brandon Barbello, and Graham Taylor. Learning human identity from motion patterns. IEEE Access, 4:1810--1820, 2016. [ bib ]
Griffin Lacey, Graham Taylor, and Shawki Areibi. Deep learning on FPGAs: Past, present, and future. arXiv preprint arXiv:1602.04283, 2016. [ bib | http ]
Weiguang Ding and Graham Taylor. Automatic moth detection from trap images for pest management. Computers and Electronics in Agriculture, 123:17--28, 2016. [ bib | DOI | http ]
Natalia Neverova, Christian Wolf, Graham Taylor, and Florian Nebout. Moddrop: adaptive multi-modal gesture recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38:1692--1706, 2016. [ bib | http ]
Natalia Neverova, Christian Wolf, Florian Nebout, and Graham Taylor. Hand pose estimation through weakly-supervised learning of a rich intermediate representation. arXiv preprint arXiv:1511.06728, 2015. [ bib | http ]
Fan Li and Graham Taylor. Alter-CNN: An approach to learning from label proportions with application to ice-water classification. In Neural Information Processing Systems 28 (NIPS) Deep Learning and Representation Learning Workshop on Learning and Privacy with Incomplete Data and Weak Supervision, 2015. [ bib | .pdf ]
Yasser Roudi and Graham Taylor. Learning with hidden variables. Current Opinion in Neurobiology, 35:110--118, 2015. [ bib | http ]
Daniel Jiwoong Im and Graham Taylor. Semi-supervised hyperspectral image classification via neighborhood graph learning. IEEE Geoscience and Remote Sensing Letters, 12(9):1913--1917, 2015. [ bib | .pdf ]
Daniel Jiwoong Im, Ethan Buchman, and Graham Taylor. An empirical investigation of minimum probability flow learning under different connectivity patterns. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2015. [ bib | http ]
Daniel Jiwoong Im and Graham Taylor. Scoring and classifying with gated auto-encoders. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2015. [ bib | http ]
Weiguang Ding, Ruoyan Wang, Fei Mao, and Graham Taylor. Theano-based large-scale visual recognition with multiple GPUs. In International Conference on Learning Representations (ICLR) Workshop Track, 2015. [ bib | http ]
Jan Rudy and Graham Taylor. Generative class-conditional autoencoders. In International Conference on Learning Representations (ICLR) Workshop Track, 2015. [ bib | .pdf ]
Matthew Veres, Griffin Lacey, and Graham Taylor. Deep learning architectures for soil property prediction. In 15th Canadian Conference on Computer and Robot Vision (CRV), pages 8--15, 2015. [ bib | .pdf ]
Jan Rudy, Weiguang Ding, Daniel Jiwoong Im, and Graham Taylor. Neural network regularization via robust weight factorization. arXiv preprint arXiv:1412.6630, 2014. [ bib | http ]
Weiguang Ding and Graham Taylor. Mental rotation by optimizing transforming distance. In Neural Information Processing Systems 27 (NIPS) Workshop on Deep Learning and Representation Learning, 2014. [ bib | http ]
Natalia Neverova, Christian Wolf, and Graham Taylor. Hand segmentation with structured convolutional learning. In Asian Conference on Computer Vision (ACCV), 2014. [ bib | .pdf ]
Natalia Neverova, Christian Wolf, Graham Taylor, and Florian Nebout. Multi-scale deep learning for gesture detection and localization. In ECCV ChaLearn Workshop on Looking at People, 2014. [ bib | .pdf ]
Terrance Devries, Kumar Biswaranjan, and Graham Taylor. Multi-task learning of facial landmarks and expression. In 14th Canadian Conference on Computer and Robot Vision (CRV), 2014. [ bib | .pdf ]
Arjun Jain, Jonathan Tompson, Mykhaylo Andriluka, Graham Taylor, and Christoph Bregler. Learning human pose estimation features with convolutional networks. In International Conference on Learning Representations (ICLR), 2014. [ bib | .pdf ]