CIFAR NCAP - Summer School 2014

Tuesday, August 12, 2014 - Saturday, August 16, 2014

Location: University of Toronto

Organizers: Geoffrey Hinton and Yoshua Bengio

Neural Computation & Adaptive Perception aims to unlock the mystery of how our brains convert sensory stimuli into information and to recreate human-style learning in computers. While this group focuses on visual systems, their research also points to broader explanations of how the brain processes other kinds of important information, including sounds, smells and tastes.

Presentations and Slides:

Tutorials

1.     Deep Learning by Yoshua Bengio (slides)

2.     Non-Gaussian Statistics and Natural Images by Aapo Hyvärinen (slides-1, slides-2)

3.     Topics in Deep Learning: Language, Imitation and Automatic Configuration by Nando de Freitas (slides-1, slides-2)

4.     Compressed Sensing and Natural Image Statistics by Yair Weiss (slides-1, slides-2)

5.     Sparse Coding in Brains and Machines by Bruno Olshausen (slides)

6.     Unsolved Problems in Vision by Bruno Olshausen (slides)

Guest Lectures

1.     Generating Sequences with Recurrent Neural Networks by Alex Graves (slides)

2.     Machine Translation with LSTMs by Ilya Sutskever (slides)

3.     Using Bayesian Optimization to Optimize Machine Learning by Ryan Adams (slides)

4.     The Geometry of RBM Training and Evaluation by Roger Grosse (slides)

5.     Dark Knowlege by Geoffrey Hinton (slides-pptx, slides-pdf)

Presentations by Participants

1.     An Autoencoder Approach to Learning Bilingual Word Representations By Stanislas Lauly (slides)

2.     Critical Points in High Dimensional Landscapes by Levent Sagun (slides)

3.     Real Time Occlusion Boundary Detection from Video by Donglai Wei (slides)

4.     Learning the Local Statistics of Optical Flow by Dan Rosenbaum (slides)

5.     Patch Statistics for Natural Image Decompositions by Ofer Springer (slides)

6.     Masked Autoencoder for Distribution Estimation (MADE) by Mathieu Germain (slides)

7.     Learning to Discover Efficient Mathematical Identities by Wojciech Zaremba (slides)

8.     Generative Models for Sentences by Amjad Almahairi (slides)

9.     Many Paths to Computing Normalizing Constants by Yuri Burda (slides)

10.   Impact of Attention on Perception by Ashkan Amiri (slides)

11.   Neural Machine Translation: Approaches, Challenges and By-Products by Kyunghyun Cho (slides)

12.   Training Neural Bayesian Nets by Laurent Dinh (slides)

13.   Pixels to Voxels: Modelling Visual Representations in the Human Brain by Pulkit Agrawal (slides)

14.   Error Correction as Data Modeling in Emerging Memory Technologies by Jesse Engel (slides)

15.   Time-series Structure in Innate Behavior by Alex Wiltschko (slides)

16.   Multimodal Learning with Deep Boltzmann Machines by Nitish Srivastava (slides)

17.   Balancing Neural Networks by Brian Cheung (slides)

18.   Generating image captions with neural networks by Ryan Kiros (slides)

19.   Learning β in β-NMF by José Sotelo (slides)

20.   Quantization of Image Features by Roni Feldman (slides)

21.   Combining Modality Specific Deep Neural Networks for Emotion Recognition in Video by Samira Ebrahimi Kahou (slides)

22.   Learning from Noisy Labels with Deep Neural Network by Sainbayar Sukhbaatar (slides)

23.   Efficient Inference of Continuous Markov Random Fields with Polynomial Potentials by Shenlong Wang (slides)

24.   Predicting Drug Response in Rheumatoid Arthritis Patients by Daniel Hidru (slides)

25.   Learning Sensory Representations For Actions by Mayur Mudigonda (slides)