Differentiable Physics (for Deep Learning), Overview Talk by Nils Thuerey
In this talk Nils explains recent research works that shows how to employ differentiable PDE solvers for deep learning. A central aim here is to improve the outcomes of numerical simulations. Results for reducing the numerical error in iterative solvers, and long-term control of physical systems are demonstrated. Source code is available at: https://github.com/tum-pbs/PhiFlow
The two research papers discussed in the talk can be found at:
https://ge.in.tum.de/publications/2020-um-solver-in-the-loop/ & https://arxiv.org/pdf/2007.00016
https://ge.in.tum.de/publications/2020-iclr-holl/ & https://arxiv.org/pdf/2001.07457
Addendum: the missing video at 33:45 is https://ge.in.tum.de/download/2020-iclr-holl/supplemental/Fig5b%20shapes%202%20refined/sequence_0.mp4 , it shows a much more "intuitive" solution compared to the single-case optimization.
Видео Differentiable Physics (for Deep Learning), Overview Talk by Nils Thuerey канала Nils Thuerey
The two research papers discussed in the talk can be found at:
https://ge.in.tum.de/publications/2020-um-solver-in-the-loop/ & https://arxiv.org/pdf/2007.00016
https://ge.in.tum.de/publications/2020-iclr-holl/ & https://arxiv.org/pdf/2001.07457
Addendum: the missing video at 33:45 is https://ge.in.tum.de/download/2020-iclr-holl/supplemental/Fig5b%20shapes%202%20refined/sequence_0.mp4 , it shows a much more "intuitive" solution compared to the single-case optimization.
Видео Differentiable Physics (for Deep Learning), Overview Talk by Nils Thuerey канала Nils Thuerey
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Nils Thuerey - Phiflow: A differentiable PDE solving framework for deep learning](https://i.ytimg.com/vi/2YUQBCIs5Mw/default.jpg)
![The Affine Particle-In-Cell Method](https://i.ytimg.com/vi/jPG5H5ZoL5Y/default.jpg)
![Finally, Differentiable Physics is Here!](https://i.ytimg.com/vi/T7w7QuYa4SQ/default.jpg)
![Automated Discovery of Mechanistic Models via Universal Differential Equations](https://i.ytimg.com/vi/AKwqJxhKkoA/default.jpg)
![But How DO Fluid Simulations Work?](https://i.ytimg.com/vi/qsYE1wMEMPA/default.jpg)
![Bayesian Neural Network | Deep Learning](https://i.ytimg.com/vi/OVne8jDKGUI/default.jpg)
![Differentiable Physical Simulation and AI @ NeurIPS 2020 DiffCVGP workshop](https://i.ytimg.com/vi/i2O72iMe9ug/default.jpg)
![Steve Brunton: "Machine Learning for Fluid Mechanics"](https://i.ytimg.com/vi/6mlhXvJlpaU/default.jpg)
![What are Differential Equations and how do they work?](https://i.ytimg.com/vi/Em339AlejIs/default.jpg)
![I Failed Orals: Let's Be Honest about the PhD Process](https://i.ytimg.com/vi/hG3gkUSdn6M/default.jpg)
![DiffTaichi: Differentiable Programming for Physical Simulation](https://i.ytimg.com/vi/Z1xvAZve9aE/default.jpg)
![Integrating Constraints into Deep Learning Architectures with Structured Layers](https://i.ytimg.com/vi/ZA5FpkYhkAI/default.jpg)
![Differentiable Programming with Julia by Mike Innes](https://i.ytimg.com/vi/LjWzgTPFu14/default.jpg)
![Andrew Ng: Advice on Getting Started in Deep Learning | AI Podcast Clips](https://i.ytimg.com/vi/1k37OcjH7BM/default.jpg)
![AN20: Partial Differential Equations Meet Deep Learning: Old Solutions for New Problems & Vice Versa](https://i.ytimg.com/vi/-PBWA1VpT1E/default.jpg)
![How Well Can DeepMind's AI Learn Physics? ⚛](https://i.ytimg.com/vi/2Bw5f4vYL98/default.jpg)
![Differentiable Physics Simulations for Deep Learning](https://i.ytimg.com/vi/yAcFwaSJQas/default.jpg)
![Visualize Temperature Dynamics of a Double Pipe Heat-Exchanger using MATLAB](https://i.ytimg.com/vi/mrndGNmU_X8/default.jpg)
![Deforming Meshes that Split and Merge, SIGGRAPH 2009](https://i.ytimg.com/vi/M5xnAdVPbgQ/default.jpg)
![Stephan Hoyer: "Improving PDE solvers and PDE-constrained optimization with deep learning and di..."](https://i.ytimg.com/vi/ysIr_csR6gA/default.jpg)