AI and Statistical/Thermal Physics
FOCUS · Q53 · ID: 1066998
Presentations
-
Self-assembly of electronic materials and the power of machine learning
ORAL · Invited
–
Presenters
-
Paulette Clancy
Johns Hopkins University
Authors
-
Paulette Clancy
Johns Hopkins University
-
-
How deep neural networks learn thermal phase transitions
ORAL
–
Publication: [1] Julian Arnold and Frank Schäfer, Phys. Rev. X 12, 031044 (2022)
Presenters
-
Frank Schäfer
CSAIL, Massachusetts Institute of Technology
Authors
-
Julian Arnold
Department of Physics, University of Basel
-
Frank Schäfer
CSAIL, Massachusetts Institute of Technology
-
-
Machine learning phases of matter: Scalability and limitations
ORAL
–
Presenters
-
Zhongzheng Tian
University of Virginia
Authors
-
Zhongzheng Tian
University of Virginia
-
Sheng Zhang
University of Virginia
-
Gia-Wei Chern
University of Virginia
-
-
Learning Together: Training Interatomic Potentials to Multiple Datasets
ORAL
–
Presenters
-
Alice Allen
Los Alamos National Lab
Authors
-
Alice Allen
Los Alamos National Lab
-
-
Local force field of thermally displaced atoms in unstable bcc iron from machine learning
ORAL
–
Presenters
-
Adrian De la Rocha Galán
University of Texas at El Paso
Authors
-
Adrian De la Rocha Galán
University of Texas at El Paso
-
Valeria I Arteaga Muniz
University of Texas at El Paso
-
Blaise A Ayirizia
The University of Texas at El Paso
-
Sofia G Gomez
University of Texas at El Paso
-
Ramon J Ravelo
University of Texas at El Paso
-
Wibe A de Jong
LBNL, Lawrence Berkeley National Laboratory
-
Jorge A Munoz
University of Texas at El Paso
-
-
CHGNet: Pretrained Neural Network Potential for Fast and Accurate Charge-constrained Molecular Dynamics
ORAL
–
Publication: Bowen Deng, "CHGNet: Pretrained Neural Network Potential for Fast and Accurate Charge-constrained Molecular Dynamics", To be submitted
Presenters
-
Bowen Deng
University of California, Berkeley
Authors
-
Bowen Deng
University of California, Berkeley
-
Peichen Zhong
University of California, Berkeley
-
Gerbrand Ceder
University of California, Berkeley
-
-
Neural-network-based interatomic potential: A case study on lithium
ORAL
–
Presenters
-
Naman Katyal
University of Texas at Austin
Authors
-
Naman Katyal
University of Texas at Austin
-
-
On-the-fly Machine Learning-Accelerated Geometry Optimization: Theoretical Screening of a Single Atom Alloy for CO<sub>2</sub> Electroreduction Reaction
ORAL
–
Presenters
-
Jiyoung Lee
University of Texas at Austin
Authors
-
Jiyoung Lee
University of Texas at Austin
-
-
Investigating the influence of local composition on properties in complex alloys using machine learned interatomic potentials
ORAL
–
Presenters
-
Megan J McCarthy
Sandia National Laboratories
Authors
-
Megan J McCarthy
Sandia National Laboratories
-
Jacob Startt
Sandia National Laboratories
-
Remi Dingreville
Sandia National Laboratories
-
Aidan P Thompson
Sandia National Laboratories
-
Mitchell A Wood
Sandia National Laboratories
-
-
Nanoparticle Heterogeneous Catalysis Dynamics Simulations with Machine Learned Force Fields
ORAL
–
Publication: CJ Owen, Y Xie, JS Lim, L. Sun, B Kozinsky, 'Morpological evolution of PdAu nanoparticles from bayesian active learning and MD simulations.' In preparation.<br>N Marcella, CJ Owen, Y Xie, AI Frenkel, B Kozinsky, RG Nuzzo, "Linking Machine-Learning Bayesian Force-Fields with XAFS to Understand Dynamic Nanomaterials under Reactive Atmospheres" In preparation.<br>CJ Owen, N Marcella Y Xie, JS Lim, L Sun, AI Frenkel, B Kozinsky, RG Nuzzo, "Complex dynamics of the CO/Pt interaction from bayesian active learning simulations and EXAFS experiments" In preparation.
Presenters
-
Cameron J Owen
Harvard University
Authors
-
Cameron J Owen
Harvard University
-
Yu Xie
Harvard University
-
Jin Soo Lim
Harvard University
-
Boris Kozinsky
Harvard University
-
-
Melting and Phase Separation of SiC from Large-scale Machine Learning Molecular Dynamics
ORAL
–
Presenters
-
Yu Xie
Harvard University
Authors
-
Yu Xie
Harvard University
-
Senja J Ramakers
Robert Bosch GmbH
-
Boris Kozinsky
Harvard University
-
-
ML models for partition functions: from the prediction of thermodynamic properties to the exploration of transition pathways
ORAL
–
Presenters
-
Caroline Desgranges
University of Massachusetts, Lowell, University of Massachusetts Lowell
Authors
-
Jerome P Delhommelle
University of Massachusetts, Lowell
-
Caroline Desgranges
University of Massachusetts, Lowell, University of Massachusetts Lowell
-
-
Diffeomorphisms invariance is a proxy of performance in deep neural networks
ORAL
–
Publication: Relative stability toward diffeomorphisms indicates performance in deep nets, L. Petrini, A. Favero, M. Geiger, M. Wyart.<br>Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
Presenters
-
Leonardo Petrini
Ecole Polytechnique Federale de Lausanne
Authors
-
Leonardo Petrini
Ecole Polytechnique Federale de Lausanne
-
Alessandro Favero
Ecole Polytechnique Federale de Lausanne
-
Mario Geiger
MIT, Swiss Federal Institute of Technology Lausanne (EPFL )
-
Matthieu Wyart
Ecole Polytechnique Federale de Lausanne
-