Neural Computation & Adaptive Perception Summer School
August 10-14, 2010
Toronto, Canada
This summer school is organized as part of the
Neural Computation & Adaptive Perception research program of CIFAR.
It is hosted by the Machine Learning group at the Department of Computer Science, University of Toronto.
Tutorials
Bruno Olshausen, "Learning about vision: things we now know, things we still don't know, and things we don't know we don't know." [Slides ], "Intermediate-level vision" [Slides]
- Readings: "How Close Are We to Understanding V1?" [pdf], "Visual Surface Representation: A Critical Link between Lower-level and Higher-level Vision" [pdf]
Siwei Lyu, "Natural Image Statistics" [Slides]
Urs Koster, "Estimating energy based models with Score Matching" [Slides]
Geoffrey Hinton, "Deep learning" [Slides]
Marc'Aurelio Ranzato, "Modeling Natural Images with Higher-Order Boltzmann Machines" [Slides]
Jascha Sohl-Dickstein, "Minimizing Probability Flow" [Slides]
Niko Troje, "Visual perception of human motion" [Slides]
David Fleet, "Human Motion Analysis" [Slides]
James Martens, "Deep Learning via Hessian-free optimization" [Slides]
Ilya Sutskever, "Training Recurrent Neural Networks to do cool stuff" [Slides]
Ryan Adams, "Monte Carlo Methods for Inference and Learning" [Slides]
Talks (send your slides to asamir@cs.toronto.edu)
- Charles Cadieu, "Learning Spatial and Transformational Invariants for Visual RepresentationSemantic Hashing" [Slides]
- Antoine Bordes, "Towards Understanding Situated Natural Language" [Slides]
- Miika Pihlaja, "Generalized Noise Contrastive Estimation" [Slides]
- Benjamin Marlin, "Inductive Principles for Restricted Boltzmann Machine Learning" [Slides]
- Razvan Pascanu, "Auto-tagging music with a discriminative RBM" [Slides]
- Daniel Zoran, "The Tree-Dependent components of natural scenes are edge filters" [Slides]
- Vida Movahedi, "Design and Perceptual Validation of Performance Measures for Salient Object Segmentation" [Slides][Code]
- Peng Guan, "Estimating Human Shape and Pose from a Single Image" [Slides]
- Patrick Li, "Learning Better Object Models using Video Data" [Slides]
- Fernando Garcia Bermudez, "Towards Indoor Navigation of a Flapping Wing Robot via Optical Flow" [Slides]
- Deqing Sun, "Secrets of Optical Flow Estimation and Their Principles" [Slides]
- Charlie Tang, "Denoising Gated Boltzmann Machines" [Slides]
- Abdel-rahman Mohamed, "Speech Recognition Using Deep Believe Networks" [Slides]
- Jo-Anne Ting, "Deep Learning of Invariant Spatiotemporal Features from Video" [Slides]
- Xing Zhang, "Study of Line Search of Learning Rate in RBM" [Slides]