Tristan Bereau: "Physics in and out of machine learning for molecular simulations: priors and pr..." скачать в хорошем качестве

Tristan Bereau: "Physics in and out of machine learning for molecular simulations: priors and pr..."

Machine Learning for Physics and the Physics of Learning 2019 Workshop II: Interpretable Learning in Physical Sciences "Physics in and out of machine learning for molecular simulations: priors and predictive constraints" Tristan Bereau - Max Planck Institute for Polymer Research, Theory Group Abstract: Advanced statistical methods are rapidly impregnating many scientific fields, offering new perspectives on long-standing problems. In materials science, data-driven methods are already bearing fruit in various disciplines, such as hard condensed matter or inorganic chemistry, as well as soft matter to a smaller extent. When coupling machine learning to molecular simulations, many problems of interest display dauntingly-large interpolation spaces, limiting their immediate application without undesired artifacts (e.g., extrapolation). The incorporation of physical information, such as conserved quantities, symmetries, and constraints, can play a decisive role in reducing the interpolation space. Conversely, physics can help determine whether an ML prediction should be trusted, acting as a more robust alternative to the predictive variance. In this talk I will show how incorporating physics in ML models for molecular simulations can help in both directions: as prior and predictive constraint. Illustrations will include advanced force fields that span large subsets of chemical space, high-throughput molecular dynamics of drug-membrane thermodynamics, and automated dimensionality reduction and clustering for molecular kinetics. Institute for Pure and Applied Mathematics, UCLA October 18, 2019 For more information: http://www.ipam.ucla.edu/mlpws2