Explore cutting-edge advancements in molecular simulation through deep learning in this 59-minute lecture by Frank Noe of Freie Universität Berlin. Delivered at IPAM's Learning and Emergence in Molecular Systems Workshop, delve into the intersection of AI and scientific research, focusing on multiscale systems and quantum chemistry. Examine machine learning applications in force fields, functionals, and quantum Monte Carlo simulations. Investigate the challenges of electronic cusps, exchange antisymmetry, and the Pauli principle. Discover the potential of normalizing flows and Boltzmann generators in enhancing sampling techniques. Gain insights into industrial applications, including benzene simulations, and understand the transformative role of machine learning in Markov State Models and stochastic normalization.
Advancing Molecular Simulation with Deep Learning - IPAM at UCLA
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Overview
Syllabus
Intro
AI for Science
How do we do things
Problems with multiscale systems
Schrodinger equation
Quantum chemistry
Machine learning force fields
Machine learning functionals
Quantum Monte Carlo
Exchange Antisymmetry
Paulinet
Electronic cusps
Artifact
Functional Flexibility
Industrial Factor
Benzene
Sampling
Markov State Models
Why Machine Learning
Normalizing Flows
Boltzmann Generators
Stochastic Normalization
Taught by
Institute for Pure & Applied Mathematics (IPAM)
Related Courses
-
Neural-Network Wave Functions for Quantum Chemistry - IPAM at UCLA
-
Extending the Reach of Quantum Monte Carlo Methods via Machine Learning
-
Quantum Monte Carlo and Machine Learning Simulations of Dense Hydrogen
-
Monte Carlo and Machine Learning Approaches in Quantum Mechanics - IPAM at UCLA
-
Molecular Electron Densities via Machine Learning - IPAM at UCLA
-
Physically Inspired Machine Learning for Excited States - IPAM at UCLA
