Machine Learning for Physics and the Physics of Learning Tutorials - IPAM

Machine Learning for Physics and the Physics of Learning Tutorials

Part of the Long Program Machine Learning for Physics and the Physics of Learning
September 5 - 10, 2019

Schedule

All times in this Schedule are Pacific Time (PT)

Thursday, September 5, 2019

Morning Session

08:00-08:55
Check-In/Light Breakfast (Hosted by IPAM)
08:55-09:00
Welcome & Opening Remarks: Dean Miguel García-Garibay (Dean of Physical Sciences, UCLA) and Dima Shlyakhtenko (Director, IPAM)
09:00-10:15
Frank Noe (MLPRC2)
Intro to Machine Learning part 1
10:15-10:45
Break
10:45-12:00
Steve Brunton (University of Washington)
Dynamical Systems part 1

Afternoon Session

12:00-12:30
Core Orientation
12:30-14:00
Lunch (on your own)
14:00-15:15
Tristan Bereau (Max Planck Institute for Polymer Research)
Constructing Conservation Laws with Machine Learning for Energy Landscapes
15:15-15:45
Break
15:45-17:00
Anatole von Lilienfeld (University of Toronto)
Introduction to Electronic Structure Calculations

Monday, September 9, 2019

Morning Session

08:00-09:00
Check-In/Light Breakfast (Hosted by IPAM)
09:00-10:15
Patrick Riley (Relay Therapeutics)
Data preparation and feature engineering
10:15-10:45
Break
10:45-12:00
Lars Ruthotto (Emory University)
Deep Neural Networks Motivated By Differential Equations I

Afternoon Session

12:00-14:00
Lunch (on your own)
14:00-15:15
Andrew Ferguson (University of Chicago)
Machine learning-enabled enhanced sampling in biomolecular simulation and data-driven design of self-assembling photonic crystals and optoelectonic π-conjugated oligopeptides
15:15-15:45
Break
15:45-17:00
Kyle Cranmer (University of Wisconsin-Madison)
The interplay between physically motivated simulations and machine learning

Tuesday, September 10, 2019

Morning Session

08:00-09:00
Check-In/Light Breakfast (Hosted by IPAM)
09:00-10:15
Patrick Riley (Relay Therapeutics)
Graph based neural networks for prediction and generation
10:15-10:45
Break
10:45-12:00
Lars Ruthotto (Emory University)
Deep Neural Networks Motivated By Differential Equations II

Afternoon Session

12:00-14:00
Lunch (on your own)
14:00-15:15
Frank Noe (MLPRC2)
Connection between Statistics and Machine Learning
15:15-15:45
Break
15:45-17:00
Steve Brunton (University of Washington)
Introduction to Fluid Mechanics
Printable Version