Machine Learning for Atomistic Simulation III: Active Learning and Uncertainty Quantification
ORAL · MAR-F50 · ID: 3104585
Presentations
-
Comparison of ensemble-based uncertainty quantification methods for neural network interatomic potential
ORAL
–
Presenters
-
Yonatan Kurniawan
Brigham Young University
Authors
-
Yonatan Kurniawan
Brigham Young University
-
Mark K Transtrum
Brigham Young University
-
Ellad B Tadmor
University of Minnesota
-
Vincenzo Lordi
Lawrence Livermore National Laboratory
-
-
Examining Uncertainty Quantification Techniques for Machine Learned Interatomic Potentials
ORAL
–
Presenters
-
Nicholas T Wimer
National Renewable Energy Laboratory (NREL)
Authors
-
Nicholas T Wimer
National Renewable Energy Laboratory (NREL)
-
Juliane Mueller
National Renewable Energy Laboratory
-
Sebastien Hamel
Lawrence Livermore National Laboratory
-
Vincenzo Lordi
Lawrence Livermore National Laboratory
-
-
Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
ORAL
–
Publication: https://doi.org/10.48550/arXiv.2404.12367
Presenters
-
Daniel Schwalbe-Koda
UCLA
Authors
-
Daniel Schwalbe-Koda
UCLA
-
Sebastien Hamel
Lawrence Livermore National Laboratory
-
Babak Sadigh
Lawrence Livermore National Laboratory
-
Fei Zhou
LLNL, Lawrence Livermore National Laboratory
-
Vincenzo Lordi
Lawrence Livermore National Laboratory
-
-
Active Learning Scheme for Accelerated Machine-Learned Interatomic Potentials Training with Enhanced Reliability: Case Studies for Strongly Anharmonic Thermal Insulators
ORAL
–
Publication: K. Kang, et al., arXiv:2409.11808
Presenters
-
Kisung Kang
Fritz Haber Institute of the Max Planck Society
Authors
-
Kisung Kang
Fritz Haber Institute of the Max Planck Society
-
Shuo Zhao
Fritz Haber Institute of the Max Planck Society
-
Thomas A R Purcell
University of Arizona
-
Christian Carbogno
Fritz Haber Institute of the Max Planck Society
-
Matthias Scheffler
The NOMAD Laboratory at FHI, Max Planck Society
-
-
Gaussian processes enhanced active learning for efficient atomic cluster expansion interatomic potential development
ORAL
–
Presenters
-
Lin H Yang
Lawrence Livermore National Laboratory
Authors
-
Lin H Yang
Lawrence Livermore National Laboratory
-
Robert E Rudd
Lawrence Livermore National Laboratory
-
Flynn Walsh
Lawrence Livermore National Laboratory
-
-
Abstract Withdrawn
ORAL Withdrawn
–
-
Uncertainty-informed transferable deep learning potentials for simulating BeF<sub>2</sub>-LiF system
ORAL
–
Publication: Liquid structure of LiF – BeF2 molten salts via<br>neutron and X-ray scattering and neural-network<br>based molecular dynamics, and structural<br>evolution with temperature
Presenters
-
Shubhojit Banerjee
UMass Lowell
Authors
-
Shubhojit Banerjee
UMass Lowell
-
Stephen Lam
UML
-
Haley Williams
University of California - Berkeley
-
Sean Fayfar
MIT
-
Raluca Scarlat
University of California, Berkeley
-
-
Active learning of interatomic potentials in the vicinity of dynamical instability for low-moduli bcc Ti-based alloys
ORAL
–
Presenters
-
Igor A. Abrikosov
Linkoping University, Linköping University
Authors
-
Igor A. Abrikosov
Linkoping University, Linköping University
-
Boburjon Mukhamedov
Linköping University
-
Elisa Richards
Linköping University
-
Amanda Ehn
Linköping University
-
Marian Arale Brännvall
Linköping University
-
Björn Alling
Linköping Univerity, Linköping University
-
Ferenc Tasnádi
Linköping University
-
-
Abstract Withdrawn
ORAL Withdrawn
–
-
Modeling Solvated Phosphoryl Transfer using Machine Learning Potentials and Transfer Learning
ORAL
–
Presenters
-
Clay H Batton
Stanford University
Authors
-
Clay H Batton
Stanford University
-
Norm M Tubman
National Aeronautics and Space Administration (NASA)
-
Brenda M Rubenstein
Brown University
-
Grant M Rotskoff
Stanford University
-
-
Capturing the Vibrational Dynamics of Acene-Based Molecular Crystals with Machine Learning
ORAL
–
Publication: Planned Paper by 12/2024 Machine Learning Force Fields for Acene-Based Molecular Crystal: Application to Host-Guest System
Presenters
-
Burak Gurlek
Max Planck Institute for the Structure & Dynamics of Matter
Authors
-
Burak Gurlek
Max Planck Institute for the Structure & Dynamics of Matter
-
Shubham Sharma
Max Planck Institute for the Structure & Dynamics of Matter
-
Paolo Lazzaroni
Max Planck Institute for the Structure & Dynamics of Matter
-
Angel Rubio
Max Planck Institute for the Structure & Dynamics of Matter, Max Planck Institute for the Structure & Dynamics of Matter; Flatiron Institute's Center for Computational Quantum Physics (CCQ) & Initiative for Computational Catalysis (ICC)
-
Mariana Rossi
Max Planck Institute for the Structure & Dynamics of Matter
-
-
On-the-fly Active Learning of ChIMES Force Fields for f-electron Materials
ORAL
–
Presenters
-
Jared C Stimac
Lawrence Livermore National Laboratory
Authors
-
Jared C Stimac
Lawrence Livermore National Laboratory
-
Nir Goldman
Lawrence Livermore National Laboratory
-
-
Exploring transformations in elemental sulfur using a machine-learned interatomic potential
ORAL
–
Presenters
-
Sonia Salomoni
Sorbonne University
Authors
-
Sonia Salomoni
Sorbonne University
-
Marco A Saitta
Sorbonne Univeristy
-
Frédéric Datchi
Sorbonne University
-
Arthur France-Lanord
Sorbonne University
-