Rose Yu - Incorporating Symmetry for Learning Spatiotemporal Dynamics
Prof. Rose Yu from UCSD speaking in the UW Data-driven methods in science and engineering seminar on Nov. 5, 2021.
Sign up for notifications of future talks: https://mailman11.u.washington.edu/mailman/listinfo/datadriven-seminar
Abstract: While deep learning has shown tremendous success in many scientific domains, it remains a grand challenge to incorporate physical principles into such models. In this talk, I will demonstrate how to incorporate symmetries into deep neural networks and significantly improve physical consistency, sample efficiency, and generalization in learning spatiotemporal dynamics. I will showcase the applications of these models to challenging problems such as turbulence forecasting and trajectory prediction for autonomous vehicles.
Видео Rose Yu - Incorporating Symmetry for Learning Spatiotemporal Dynamics канала Physics Informed Machine Learning
Sign up for notifications of future talks: https://mailman11.u.washington.edu/mailman/listinfo/datadriven-seminar
Abstract: While deep learning has shown tremendous success in many scientific domains, it remains a grand challenge to incorporate physical principles into such models. In this talk, I will demonstrate how to incorporate symmetries into deep neural networks and significantly improve physical consistency, sample efficiency, and generalization in learning spatiotemporal dynamics. I will showcase the applications of these models to challenging problems such as turbulence forecasting and trajectory prediction for autonomous vehicles.
Видео Rose Yu - Incorporating Symmetry for Learning Spatiotemporal Dynamics канала Physics Informed Machine Learning
Показать
Комментарии отсутствуют
Информация о видео
9 ноября 2021 г. 21:27:38
01:01:06
Другие видео канала
Benjamin Peherstorfer - Physics-based machine learning for quickly simulating transport-dominated...
Aditya Nair/Floris van Breugel - Leveraging Machine Learning for interaction-based models and contro
Melanie Weber - Exploiting Geometric Structure in Machine Learning and Optimization
Na Li - Scalable and Safe Learning-based Decision-Making in Dynamical Systems
Alex Gorodetsky - Scalable Learning of Dynamical Systems
Hod Lipson - The AI Scientist Automating Discovery, From Cognitive Robotics to Computational Biology
Steve Brunton - Discovering interpretable and generalizable dynamical systems from data
Jane Bae - Wall-models of turbulent flows via scientific multi-agent reinforcement learning
Kathleen Champion - Data-driven discovery of coordinates and governing equations
Kevin Carlberg - Breaking Komolgorov-Width Barriers using Deep Learning
David Bortz - The Surprising Robustness and Computational Efficiency of Weak Form System Identif...
John Wright - Deep Networks and the Multiple Manifold Problem
Dominique Zosso - Graph-Based Geometric Data Analysis
Laure Zanna - Data-driven turbulence closures for ocean and climate models: advances and challenges
Benjamin Peherstorfer - Data generation for learning reduced models with operator inference
Andrea Bertozzi - Total Variation Minimization on Graphs for Semisupervised and Unsupervised ML
Andrew Stuart - Supervised Learning For Operators
Krithika Manohar - Optimal Sensors for Empowering AI
Jörn Dunkel - Symmetry-informed model inference for active matter
Aleksandr Aravkin - Algorithms for Nonsmooth, Nonconvex Problems in Data-Driven Discovery