Michele Ceriotti: "Machine learning for atomic and molecular simulations"
Machine Learning for Physics and the Physics of Learning 2019
Workshop IV: Using Physical Insights for Machine Learning
"Machine learning for atomic and molecular simulations"
Michele Ceriotti - École Polytechnique Fédérale de Lausanne (EPFL)
Abstract: Machine learning is finding applications to more and more tasks, in science as much as in everyday life. In this talk I will focus on how atomic and molecular simulations are being transformed by the use of statistical regression models, that make it possible to approximate accurately and efficiently atomistic properties computed from a few reference electronic-structure calculations. I will argue about the advantages that are brought about by a physically-motivated framework, and about the insights that can be obtained by a critical application of ML methods. Examples will be given spanning molecular and condensed matter systems, and properties as diverse as magnetic nuclear chemical shieldings and the electron charge density, underscoring the general applicability of the approach.
Institute for Pure and Applied Mathematics, UCLA
November 18, 2019
For more information: http://www.ipam.ucla.edu/mlpws4
Видео Michele Ceriotti: "Machine learning for atomic and molecular simulations" канала Institute for Pure & Applied Mathematics (IPAM)
Workshop IV: Using Physical Insights for Machine Learning
"Machine learning for atomic and molecular simulations"
Michele Ceriotti - École Polytechnique Fédérale de Lausanne (EPFL)
Abstract: Machine learning is finding applications to more and more tasks, in science as much as in everyday life. In this talk I will focus on how atomic and molecular simulations are being transformed by the use of statistical regression models, that make it possible to approximate accurately and efficiently atomistic properties computed from a few reference electronic-structure calculations. I will argue about the advantages that are brought about by a physically-motivated framework, and about the insights that can be obtained by a critical application of ML methods. Examples will be given spanning molecular and condensed matter systems, and properties as diverse as magnetic nuclear chemical shieldings and the electron charge density, underscoring the general applicability of the approach.
Institute for Pure and Applied Mathematics, UCLA
November 18, 2019
For more information: http://www.ipam.ucla.edu/mlpws4
Видео Michele Ceriotti: "Machine learning for atomic and molecular simulations" канала Institute for Pure & Applied Mathematics (IPAM)
Показать
Комментарии отсутствуют
Информация о видео
11 декабря 2019 г. 3:34:07
00:53:41
Другие видео канала
Graphene science | Mikael Fogelström | TEDxGöteborgVariational methods and deep learning for high-dimensional dynamical systemsModeling the Quantum Nature of Atomic Nuclei by Imaginary Time Path Integrals - Lecture 1MDAnalysis: A Python Package for the Rapid Analysis of Molecular Dynamics Simulations | SciPy 2016SELFIES: A 100% robust molecular string representation for Machine Learning in Chemistry, M. KrennJohn Kitchin: Using Machine Learning to Improve Molecular SimulationsProf. Brian Cox - Machine Learning & Artificial Intelligence - Royal SocietyWhy graphene hasn’t taken over the world...yetInteratomic potentials from first principlesMichael Craig - Machine Learning on molecular dataML4Science Seminar: Michele Ceriotti (EPFL)Physics-inspired Machine Learning for Materials Discovery | AI & Molecular World | Michele CeriottiICTP-EAIFR Colloquium on "Machine learning and molecular dynamics"Deep learning on graphs: successes, challenges, and next steps | Graph Neural NetworksStéphane Mallat: "Scattering Invariant Deep Networks for Classification, Pt. 1"1. Introduction to Human Behavioral Biology11. Introduction to Machine LearningStefano Soatto: "Invariance and disentanglement in deep representations"James Zou: "Deep learning for genomics: Introduction and examples"High Speed Protein Simulations with Anton