Deep Learning to Discover Coordinates for Dynamics: Autoencoders & Physics Informed Machine Learning
Joint work with Nathan Kutz: https://www.youtube.com/channel/UCoUOaSVYkTV6W4uLvxvgiFA
Discovering physical laws and governing dynamical systems is often enabled by first learning a new coordinate system where the dynamics become simple. This is true for the heliocentric Copernican system, which enabled Kepler's laws and Newton's F=ma, for the Fourier transform, which diagonalizes the heat equation, and many others. In this video, we discuss how deep learning is being used to discover effective coordinate systems where simple dynamical systems models may be discovered.
@eigensteve on Twitter
eigensteve.com
databookuw.com
Some useful papers:
https://www.pnas.org/content/116/45/22445 [SINDy + Autoencoders]
https://www.nature.com/articles/s41467-018-07210-0 [Koopman + Autoencoders]
https://arxiv.org/abs/2102.12086 [Koopman Review Paper]
Видео Deep Learning to Discover Coordinates for Dynamics: Autoencoders & Physics Informed Machine Learning канала Steve Brunton
Discovering physical laws and governing dynamical systems is often enabled by first learning a new coordinate system where the dynamics become simple. This is true for the heliocentric Copernican system, which enabled Kepler's laws and Newton's F=ma, for the Fourier transform, which diagonalizes the heat equation, and many others. In this video, we discuss how deep learning is being used to discover effective coordinate systems where simple dynamical systems models may be discovered.
@eigensteve on Twitter
eigensteve.com
databookuw.com
Some useful papers:
https://www.pnas.org/content/116/45/22445 [SINDy + Autoencoders]
https://www.nature.com/articles/s41467-018-07210-0 [Koopman + Autoencoders]
https://arxiv.org/abs/2102.12086 [Koopman Review Paper]
Видео Deep Learning to Discover Coordinates for Dynamics: Autoencoders & Physics Informed Machine Learning канала Steve Brunton
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Sparse Identification of Nonlinear Dynamics (SINDy): Sparse Machine Learning Models 5 Years Later!](https://i.ytimg.com/vi/NxAn0oglMVw/default.jpg)
![Variational Autoencoders](https://i.ytimg.com/vi/9zKuYvjFFS8/default.jpg)
![The Anatomy of a Dynamical System](https://i.ytimg.com/vi/-FvrON0OmYc/default.jpg)
![Singular Value Decomposition (SVD): Mathematical Overview](https://i.ytimg.com/vi/nbBvuuNVfco/default.jpg)
![How Well Can DeepMind's AI Learn Physics? ⚛](https://i.ytimg.com/vi/2Bw5f4vYL98/default.jpg)
![](https://i.ytimg.com/vi/YO_MGvhXmKQ/default.jpg)
![Simple Explanation of AutoEncoders](https://i.ytimg.com/vi/3jmcHZq3A5s/default.jpg)
![Reinforcement Learning: Machine Learning Meets Control Theory](https://i.ytimg.com/vi/0MNVhXEX9to/default.jpg)
![Data-driven model discovery: Targeted use of deep neural networks for physics and engineering](https://i.ytimg.com/vi/gUxBJU5n2Zs/default.jpg)
![Encoder Decoder Network - Computerphile](https://i.ytimg.com/vi/1icvxbAoPWc/default.jpg)
![What is an Autoencoder? | Two Minute Papers #86](https://i.ytimg.com/vi/Rdpbnd0pCiI/default.jpg)
![Math's Fundamental Flaw](https://i.ytimg.com/vi/HeQX2HjkcNo/default.jpg)
![Robust Principal Component Analysis (RPCA)](https://i.ytimg.com/vi/yDpz0PqULXQ/default.jpg)
![Neural Network Architectures & Deep Learning](https://i.ytimg.com/vi/oJNHXPs0XDk/default.jpg)
![Gradient descent, how neural networks learn | Chapter 2, Deep learning](https://i.ytimg.com/vi/IHZwWFHWa-w/default.jpg)
![What Are Physics Informed Neural Networks (PINNs) ?](https://i.ytimg.com/vi/8YUZQO5ZmaY/default.jpg)
![The Most Realistic Humanoid Robot Yet (Ameca)](https://i.ytimg.com/vi/BpnnD_0IlbE/default.jpg)
![Why don't they teach Newton's calculus of 'What comes next?'](https://i.ytimg.com/vi/4AuV93LOPcE/default.jpg)
![Deep Learning of Dynamics and Coordinates with SINDy Autoencoders](https://i.ytimg.com/vi/WHhDgxkiR9c/default.jpg)
![The Weird World in RGB](https://i.ytimg.com/vi/uYbdx4I7STg/default.jpg)