Workshop III: Surrogate Models and Coarsening Techniques

October 30 - November 3, 2017

Schedule


Monday, October 30, 2017

9:00 - 9:40
Gregory Voth (University of Chicago)

Ultra-Coarse-Graining and Its Applications
PDF Presentation

 
10:15 - 10:55
Gabor Csanyi (University of Cambridge)

How do we build good databases for machine learning of force fields?

 
11:30 - 12:10
Harald Oberhofer (Technical University Munich (TUM))

Embedding Quantum Regions into Classical Environments
PDF Presentation

 
2:30 - 3:10
4:00 - 4:40
Imre Risi Kondor (University of Chicago)

Covariant neural networks for learning graphs and atomic potentials


Tuesday, October 31, 2017

9:00 - 9:40
10:15 - 10:55
11:30 - 12:10
2:30 - 3:10

Wednesday, November 1, 2017

9:00 - 9:40
10:15 - 10:55
Albert Bartok-Partay (Science and Technology Facilities Council)

Learning interactions from microscopic observables
PDF Presentation

 
11:30 - 12:10
2:30 - 3:10
4:00 - 4:40
David Bindel (Cornell University)

Scalable algorithms for kernel-based surrogates in prediction and optimization
PDF Presentation

 

Thursday, November 2, 2017

9:00 - 9:40
Mark Tuckerman (New York University)

Exploration and learning of energy and free energy landscapes

 
10:15 - 10:55
Steve Brunton (University of Washington)

Data-driven characterization and control of complex systems
PDF Presentation

 
11:30 - 12:10
Olexandr Isayev (University of North Carolina)

Towards Universal ML Potential for Organic Molecules

 
2:30 - 3:10
Gus Hart (Brigham Young University)

Extending the SOAP descriptor to make alloy GAP potentials

 
4:00 - 4:40
Gareth Conduit (University of Cambridge)

Who needs atoms to design materials?

 

Friday, November 3, 2017

9:00 - 9:40
10:15 - 10:55
Cecilia Clementi (Rice University)

Incorporating Experimental Data in Long Timescales Macromolecular Simulations

 
11:30 - 12:10
Thomas Miller (California Institute of Technology)

Development of a coarse-grained model for co-translational membrane protein folding

2:30 - 3:10
Richard Hennig (University of Florida)

Machine-learning of crystal structure energy landscapes