Physics-based Deep Learning

Physics-based Deep Learning. Thuerey, N., Holl, P., Mueller, M., Schnell, P., Trost, F., & Um, K. arXiv:2109.05237 [physics], September, 2021. arXiv: 2109.05237

Paper abstract bibtex

This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. As much as possible, all topics come with hands-on code examples in the form of Jupyter notebooks to quickly get started. Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling. We live in exciting times: these methods have a huge potential to fundamentally change what computer simulations can achieve.

@article{thuerey_physics-based_2021,
	title = {Physics-based {Deep} {Learning}},
	url = {http://arxiv.org/abs/2109.05237},
	abstract = {This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. As much as possible, all topics come with hands-on code examples in the form of Jupyter notebooks to quickly get started. Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling. We live in exciting times: these methods have a huge potential to fundamentally change what computer simulations can achieve.},
	urldate = {2021-09-15},
	journal = {arXiv:2109.05237 [physics]},
	author = {Thuerey, Nils and Holl, Philipp and Mueller, Maximilian and Schnell, Patrick and Trost, Felix and Um, Kiwon},
	month = sep,
	year = {2021},
	note = {arXiv: 2109.05237},
	keywords = {Computer Science - Machine Learning, Physics - Computational Physics},
}

Downloads: 0

{"_id":"BRfaRXBMvEe8PCjY4","bibbaseid":"thuerey-holl-mueller-schnell-trost-um-physicsbaseddeeplearning-2021","author_short":["Thuerey, N.","Holl, P.","Mueller, M.","Schnell, P.","Trost, F.","Um, K."],"bibdata":{"bibtype":"article","type":"article","title":"Physics-based Deep Learning","url":"http://arxiv.org/abs/2109.05237","abstract":"This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. As much as possible, all topics come with hands-on code examples in the form of Jupyter notebooks to quickly get started. Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling. We live in exciting times: these methods have a huge potential to fundamentally change what computer simulations can achieve.","urldate":"2021-09-15","journal":"arXiv:2109.05237 [physics]","author":[{"propositions":[],"lastnames":["Thuerey"],"firstnames":["Nils"],"suffixes":[]},{"propositions":[],"lastnames":["Holl"],"firstnames":["Philipp"],"suffixes":[]},{"propositions":[],"lastnames":["Mueller"],"firstnames":["Maximilian"],"suffixes":[]},{"propositions":[],"lastnames":["Schnell"],"firstnames":["Patrick"],"suffixes":[]},{"propositions":[],"lastnames":["Trost"],"firstnames":["Felix"],"suffixes":[]},{"propositions":[],"lastnames":["Um"],"firstnames":["Kiwon"],"suffixes":[]}],"month":"September","year":"2021","note":"arXiv: 2109.05237","keywords":"Computer Science - Machine Learning, Physics - Computational Physics","bibtex":"@article{thuerey_physics-based_2021,\n\ttitle = {Physics-based {Deep} {Learning}},\n\turl = {http://arxiv.org/abs/2109.05237},\n\tabstract = {This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. As much as possible, all topics come with hands-on code examples in the form of Jupyter notebooks to quickly get started. Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling. We live in exciting times: these methods have a huge potential to fundamentally change what computer simulations can achieve.},\n\turldate = {2021-09-15},\n\tjournal = {arXiv:2109.05237 [physics]},\n\tauthor = {Thuerey, Nils and Holl, Philipp and Mueller, Maximilian and Schnell, Patrick and Trost, Felix and Um, Kiwon},\n\tmonth = sep,\n\tyear = {2021},\n\tnote = {arXiv: 2109.05237},\n\tkeywords = {Computer Science - Machine Learning, Physics - Computational Physics},\n}\n\n","author_short":["Thuerey, N.","Holl, P.","Mueller, M.","Schnell, P.","Trost, F.","Um, K."],"key":"thuerey_physics-based_2021","id":"thuerey_physics-based_2021","bibbaseid":"thuerey-holl-mueller-schnell-trost-um-physicsbaseddeeplearning-2021","role":"author","urls":{"Paper":"http://arxiv.org/abs/2109.05237"},"keyword":["Computer Science - Machine Learning","Physics - Computational Physics"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["SZvSgtLYdBsPSQ3NM","iwKepCrWBps7ojhDx"],"keywords":["computer science - machine learning","physics - computational physics"],"search_terms":["physics","based","deep","learning","thuerey","holl","mueller","schnell","trost","um"],"title":"Physics-based Deep Learning","year":2021}