Machine Learning for Physics and the Physics of Learning Tutorials

September 5 - 10, 2019

Schedule


Thursday, September 5, 2019

9:00 - 10:15
Frank Noe (Freie Universität Berlin)

Intro to Machine Learning part 1
PDF Presentation

 
10:45 - 12:00
Steve Brunton (University of Washington)

Dynamical Systems part 1
PDF Presentation

 
2:00 - 3:15
Tristan Bereau (Max Planck Institute for Polymer Research)

Constructing Conservation Laws with Machine Learning for Energy Landscapes
PDF Presentation

 
3:45 - 5:00
Anatole von Lilienfeld (University of Basel)

Introduction to Electronic Structure Calculations

 

Friday, September 6, 2019

9:00 - 10:15
Frank Noe (Freie Universität Berlin)

Intro to Machine Learning part 2
PDF Presentation

 
10:45 - 12:00
Steve Brunton (University of Washington)

Dynamical Systems part 2
PDF Presentation

 
2:00 - 3:15
Marina Meila (University of Washington)

Manifold Learning
PDF Presentation

 
3:45 - 5:00
Gianni De Fabritiis (Universitat Pompeu Fabra)

Machine Learning for Drug Design

 

Monday, September 9, 2019

9:00 - 10:15
Patrick Riley (Google)

Data preparation and feature engineering

10:45 - 12:00
2:00 - 3:15
3:45 - 5:00
Kyle Cranmer (New York University)

The interplay between physically motivated simulations and machine learning
PDF Presentation

 

Tuesday, September 10, 2019

9:00 - 10:15
Patrick Riley (Google)

Graph based neural networks for prediction and generation

10:45 - 12:00
2:00 - 3:15
Frank Noe (Freie Universität Berlin)

Connection between Statistics and Machine Learning
PDF Presentation

 
3:45 - 5:00
Steve Brunton (University of Washington)

Introduction to Fluid Mechanics
PDF Presentation