New Deep Learning Techniques

February 5 - 9, 2018

Schedule


Monday, February 5, 2018

9:00 - 9:40
10:10 - 10:50
11:20 - 12:00
Ellie Pavlick (University of Pennsylvania)

Should we care about linguistics?
PDF Presentation

 
2:00 - 2:40
Leonidas Guibas (Stanford University)

Knowledge Transport Over Visual Data

4:30 - 5:30 Please note different location: Ackerman Grand Ballroom

Tuesday, February 6, 2018

9:00 - 9:40
10:10 - 10:50
11:20 - 12:00
Kyle Cranmer (New York University)

Deep Learning in the Physical Sciences
PDF Presentation

 
2:00 - 2:40
Stéphane Mallat (École Normale Supérieure)

Deep Generative Networks as Inverse Problems

 
3:00 - 3:40
Michael Elad (Technion - Israel Institute of Technology)

Sparse Modeling in Image Processing and Deep Learning
PDF Presentation

 
4:30 - 5:30 Please note different location: Ackerman Grand Ballroom

Wednesday, February 7, 2018

9:00 - 9:40
Xavier Bresson (Nanyang Technological University, Singapore)

Convolutional Neural Networks on Graphs
PDF Presentation

 
10:10 - 10:50
11:20 - 12:00
2:00 - 2:40
Jure Leskovec (Stanford University)

Large-scale Graph Representation Learning
PDF Presentation

 
3:10 - 3:50
Arthur Szlam (Facebook)

Composable planning with attributes

 
4:20 - 5:00
Yann LeCun (New York University)

A Few (More) Approaches to Unsupervised Learning

 

Thursday, February 8, 2018

9:00 - 9:40
Sanja Fidler (University of Toronto)

Teaching Machines with Humans in the Loop

10:10 - 10:50
Raquel Urtasun (University of Toronto)

Deep Learning for Self-Driving Cars

11:20 - 12:00
Pratik Chaudhari (University of California, Los Angeles (UCLA))

Unraveling the mysteries of stochastic gradient descent on deep networks
PDF Presentation

 
2:00 - 2:40
Stefano Soatto (University of California, Los Angeles (UCLA))

Emergence Theory of Deep Learning

 
3:10 - 3:50
Tom Goldstein (University of Maryland)

What do neural net loss functions look like?

 
4:20 - 5:00

Friday, February 9, 2018

9:00 - 9:40
9:50 - 10:30
11:00 - 11:40
Zuowei Shen (National University of Singapore)

Deep Learning: Approximation of functions by composition
PDF Presentation

 
11:50 - 12:30