Designing Neural Networks for the Structure of Physics Data
FOCUS · K53 · ID: 1067006
Presentations
-
Unified Graph Neural Network Force-field for the Periodic Table
ORAL · Invited
–
Presenters
-
Kamal Choudhary
- National Institute of Standards and Tech
Authors
-
Kamal Choudhary
- National Institute of Standards and Tech
-
-
Structure-motif-based material network for functional material discovery.
ORAL
–
Presenters
-
Anoj Aryal
- Northeastern University
Authors
-
Anoj Aryal
- Northeastern University
-
Huta Banjade
- Virginia Commonwealth University
-
Qimin Yan
- Northeastern University
-
-
Physically informed graph neural networks for prediction of optical properties of solid materials
ORAL
–
Presenters
-
Can Ataca
- University of Maryland, Baltimore County
Authors
-
Can Ataca
- University of Maryland, Baltimore County
-
Akram Ibrahim
- University of Maryland Baltimore County
-
-
Mario Geiger
ORAL · Invited
–
Presenters
-
Mario Geiger
- MIT
- Swiss Federal Institute of Technology Lausanne (EPFL )
Authors
-
Mario Geiger
- MIT
- Swiss Federal Institute of Technology Lausanne (EPFL )
-
-
Understanding Self-Assembly Behavior with Self-Supervised Learning
ORAL
–
Publication: https://arxiv.org/abs/2110.02393 ; also a more tailored preprint that is under review as of submission
Presenters
-
Matthew Spellings
- Vector Institute for Artificial Intelligence
Authors
-
Matthew Spellings
- Vector Institute for Artificial Intelligence
-
Maya Martirossyan
- Cornell University
-
Julia Dshemuchadse
- Cornell University
-
-
Metric geometry tools for automatic structure phase map generation
ORAL
–
Presenters
-
Kiran Vaddi
- University of Washington
Authors
-
Kiran Vaddi
- University of Washington
-
Karen Li
- University of Washington
-
Lilo Pozzo
- University of Washington
-
-
Graph neural network accelerated generalizable stress field prediction for mesh-based finite element simulations
ORAL
–
Presenters
-
Bowen Zheng
- University of California at Berkeley
- University of California, Berkeley
Authors
-
Bowen Zheng
- University of California at Berkeley
- University of California, Berkeley
-
Zeqing Jin
- University of California, Berkeley
-
Changgon Kim
- Hyundai Motor Company
-
Grace X Gu
- University of California at Berkeley
- University of California, Berkeley
-
-
Modeling the Band Structure of Periodic Crystals with Physics-Informed Neural Networks
ORAL
–
Presenters
-
Circe Hsu
- Northeastern University
Authors
-
Circe Hsu
- Northeastern University
-
Daniel T Larson
- Harvard University
- Department of Physics, Harvard University
-
Gabriel R Schleder
- Harvard University
-
Marios Mattheakis
- Harvard University
-
Efthimios Kaxiras
- Harvard University
-
-
Using CycleGANs to construct training data for other Machine Learning models
ORAL
–
Presenters
-
Abid A Khan
- University of Illinois at Urbana-Champai
Authors
-
Abid A Khan
- University of Illinois at Urbana-Champai
-
Chia-Hao Lee
- University of Illinois at Urbana-Champaign
-
Pinshane Y Huang
- University of Illinois at Urbana-Champaign
-
Bryan K Clark
- University of Illinois at Urbana-Champaign
-
-
Contrastive Learning Reveals the Trajectory of Protein Structure Evolution
ORAL
–
Presenters
-
Yong Wei
- High Point University
Authors
-
Yong Wei
- High Point University
-
Baofu Qiao
- City University of New York
-
Tao Wei
- Howard University
-
Hanning Chen
- The University of Texas at Austin
-
-
Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics
ORAL
–
Publication: Title: GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions. Authors: Ryan Lopez and Paul J. Atzberger. (Submitted to JMLR, arxiv link: https://arxiv.org/pdf/2206.05183.pdf)
Presenters
-
Ryan Lopez
- Massachusetts Institute of Technology
Authors
-
Ryan Lopez
- Massachusetts Institute of Technology
-
Paul J Atzberger
- University of California, Santa Barbara
-