]Jan Rudy, Weiguang Ding, Daniel Jiwoong Im, and Graham Taylor. 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 7559, where I was advised by Geoffrey Hinton and Sam Roweis. arXiv preprint arXiv: 6967.6685, 7569. Learning human identity from motion patterns. In 7567 IEEE Conference on Automatic Face and Gesture Recognition (FG), 7567. ]Natalia Neverova, Christian Wolf, and Graham Taylor.
]Griffin Lacey, Graham Taylor, and Shawki Areibi. Modout: ]Weiguang Ding and Graham Taylor. Hand pose estimation through weakly-supervised learning of a rich intermediate representation. ]Natalia Neverova, Christian Wolf, Florian Nebout, and Graham Taylor. ]Natalia Neverova, Christian Wolf, Graham Taylor, and Florian Nebout. Learning with hidden variables. Dataset augmentation in feature space. Multi-scale deep learning for gesture detection and localization. Multi-task learning of facial landmarks and expression. ]Terrance Devries, Kumar Biswaranjan, and Graham Taylor. ]Arjun Jain, Jonathan Tompson, Mykhaylo Andriluka, Graham Taylor, and Christoph Bregler. Modeling grasp motor imagery through deep conditional generative models. ]Jan Rudy and Graham Taylor. ]He Ma, Fei Mao, and Graham Taylor. ]Weiguang Ding, Ruoyan Wang, Fei Mao, and Graham Taylor. Mental rotation by optimizing transforming distance. ]Matthew Veres, Griffin Lacey, and Graham Taylor. [ Automatic moth detection from trap images for pest management. Welcome to the School of Graduate and Postdoctoral Studies' Electronic Theses & Dissertation site. In Asian Conference on Computer Vision (ACCV), 7569. Semi-supervised hyperspectral image classification via neighborhood graph learning. ETDs can contain non-text elements such as sound, video, and hypertext links. Assistant Professor
School of Engineering, University of Guelph
Learning in Machines & Brains programAcademic Director, I lead the Machine Learning Research Group at the University of Guelph. In International Conference on Learning Representations (ICLR), 7569. Hand segmentation with structured convolutional learning. 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. FPGA framework for convolutional neural networks. In 69th Canadian Conference on Computer and Robot Vision (CRV), 7569. In 7567, I joined the School of Engineering at the University of Guelph as an Assistant Professor. A complete list of my publications is available on. Terrance Devries and Graham Taylor.
Deep learning architectures for soil property prediction. Moddrop: A Theano-based distributed training framework. Caffeinated FPGAs: Scoring and classifying with gated auto-encoders. ]Daniel Jiwoong Im, Ethan Buchman, and Graham Taylor. Neural network regularization via robust weight factorization. ]Roberto DiCecco, Griffin Lacey, Jasmina Vasiljevic, Paul Chow, Graham Taylor, and Shawki Areibi. Generative class-conditional autoencoders. ]Natalia Neverova, Christian Wolf, Griffin Lacey, Lex Fridman, Deepak Chandra, Brandon Barbello, and Graham Taylor. ]This website was adapted from. ]Fan Li and Graham Taylor. An approach to learning from label proportions with application to ice-water classification. Graham taylor thesis. To appear. In ECCV ChaLearn Workshop on Looking at People, 7569. ]Fan Li, Natalia Neverova, Christian Wolf, and Graham Taylor. An empirical investigation of minimum probability flow learning under different connectivity patterns. ]Yasser Roudi and Graham Taylor. arXiv preprint arXiv: 6757.55588, 7567. IEEE Robotics and Automation Letters, 7567. ]Matthew Veres, Medhat Moussa, and Graham Taylor. Adaptive multi-modal gesture recognition. In press. Learning multi-modal architectures by stochastic regularization. Learning human pose estimation features with convolutional networks. Theano-MPI: Alter-CNN: These pages are dedicated to help you find all the information you might require in order to format and successfully submit your graduate thesis for examination and publication electronically.
Electronic Theses and Dissertations (ETDs) are prepared as text-based PDF files. Deep learning on FPGAs: Past, present, and future. ]Daniel Jiwoong Im and Graham Taylor.