Interpretable Deep Learning for New Physics Discovery
In this video, Miles Cranmer discusses a method for converting a neural network into an analytic equation using a particular set of inductive biases. The technique relies on a sparsification of latent spaces in a deep neural network, followed by symbolic regression. In their paper, they demonstrate that they can recover physical laws for various simple and complex systems. For example, they discover gravity along with planetary masses from data; they learn a technique for doing cosmology with cosmic voids and dark matter halos; and they show how to extract the Euler equation from a graph neural network trained on turbulence data.
Paper: https://arxiv.org/abs/2006.11287
Blogpost: https://astroautomata.com/paper/symbolic-neural-nets/
Code and interactive demo: https://github.com/MilesCranmer/symbolic_deep_learning
Personal website: https://astroautomata.com/
Twitter: @MilesCranmer
%%% CHAPTERS %%%
0:00 Introduction
1:51 Symbolic Regression Intro
5:38 Genetic Algorithms for Symbolic Regression
7:49 PySR for Symbolic Regression
9:09 Combining Deep Learning and Symbolic Regression
14:05 Graph Neural Networks
16:39 Recovering Physics from a GNN
18:39 Results on Unknown Systems
23:12 Takeaways
Видео Interpretable Deep Learning for New Physics Discovery канала Steve Brunton
Paper: https://arxiv.org/abs/2006.11287
Blogpost: https://astroautomata.com/paper/symbolic-neural-nets/
Code and interactive demo: https://github.com/MilesCranmer/symbolic_deep_learning
Personal website: https://astroautomata.com/
Twitter: @MilesCranmer
%%% CHAPTERS %%%
0:00 Introduction
1:51 Symbolic Regression Intro
5:38 Genetic Algorithms for Symbolic Regression
7:49 PySR for Symbolic Regression
9:09 Combining Deep Learning and Symbolic Regression
14:05 Graph Neural Networks
16:39 Recovering Physics from a GNN
18:39 Results on Unknown Systems
23:12 Takeaways
Видео Interpretable Deep Learning for New Physics Discovery канала Steve Brunton
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Reinforcement Learning: Machine Learning Meets Control TheoryNeural Network Architectures & Deep LearningTurbulence Closure Models: Reynolds Averaged Navier Stokes (RANS) & Large Eddy Simulations (LES)21. Eigenvalues and EigenvectorsA Physics Prof Bet Me $10,000 I'm Wrong2020's Biggest Breakthroughs in PhysicsShannon Nyquist Sampling TheoremThe Story of Shor's Algorithm, Straight From the Source | Peter ShorWhat Is Turbulence? Turbulent Fluid Dynamics are EverywhereICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M BronsteinIntro to graph neural networks (ML Tech Talks)Conquering my academic demonData-Driven Control: The Goal of Balanced Model ReductionDeep Reinforcement Learning: Neural Networks for Learning Control LawsDr. Michio Kaku Answers Physics Questions From Twitter | Tech Support | WIREDMIT Introduction to Deep Learning | 6.S191Sparse Sensor Placement Optimization for ReconstructionTurbulence is Everywhere! Examples of Turbulence and Canonical FlowsMachine Learning for Fluid Dynamics: Models and Control