@article{udrescu2020,
	title = {{AI} {Feynman}: {A} physics-inspired method for symbolic regression},
	volume = {6},
	copyright = {Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.},
	issn = {2375-2548},
	shorttitle = {{AI} {Feynman}},
	url = {https://advances.sciencemag.org/content/6/16/eaay2631},
	doi = {10.1126/sciadv.aay2631},
	abstract = {A core challenge for both physics and artificial intelligence (AI) is symbolic regression: finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions of practical interest often exhibit symmetries, separability, compositionality, and other simplifying properties. In this spirit, we develop a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques. We apply it to 100 equations from the Feynman Lectures on Physics, and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult physics-based test set, we improve the state-of-the-art success rate from 15 to 90\%.
Our physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers.
Our physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers.},
	language = {en},
	number = {16},
	urldate = {2020-04-23},
	journal = {Science Advances},
	author = {Udrescu, Silviu-Marian and Tegmark, Max},
	month = apr,
	year = {2020},
	note = {Publisher: American Association for the Advancement of Science
Section: Research Article},
	keywords = {david, neuroblox: scientific ML},
	pages = {eaay2631},
	file = {Full Text PDF:/Users/lcneuro/Zotero/storage/D3IWBJCH/Udrescu and Tegmark - 2020 - AI Feynman A physics-inspired method for symbolic.pdf:application/pdf;Snapshot:/Users/lcneuro/Zotero/storage/4LPC9RAD/eaay2631.html:text/html},
}

{"_id":"QvcbL9YW4A9KXozow","bibbaseid":"udrescu-tegmark-aifeynmanaphysicsinspiredmethodforsymbolicregression-2020","author_short":["Udrescu, S.","Tegmark, M."],"bibdata":{"bibtype":"article","type":"article","title":"AI Feynman: A physics-inspired method for symbolic regression","volume":"6","copyright":"Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.","issn":"2375-2548","shorttitle":"AI Feynman","url":"https://advances.sciencemag.org/content/6/16/eaay2631","doi":"10.1126/sciadv.aay2631","abstract":"A core challenge for both physics and artificial intelligence (AI) is symbolic regression: finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions of practical interest often exhibit symmetries, separability, compositionality, and other simplifying properties. In this spirit, we develop a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques. We apply it to 100 equations from the Feynman Lectures on Physics, and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult physics-based test set, we improve the state-of-the-art success rate from 15 to 90%. Our physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers. Our physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers.","language":"en","number":"16","urldate":"2020-04-23","journal":"Science Advances","author":[{"propositions":[],"lastnames":["Udrescu"],"firstnames":["Silviu-Marian"],"suffixes":[]},{"propositions":[],"lastnames":["Tegmark"],"firstnames":["Max"],"suffixes":[]}],"month":"April","year":"2020","note":"Publisher: American Association for the Advancement of Science Section: Research Article","keywords":"david, neuroblox: scientific ML","pages":"eaay2631","file":"Full Text PDF:/Users/lcneuro/Zotero/storage/D3IWBJCH/Udrescu and Tegmark - 2020 - AI Feynman A physics-inspired method for symbolic.pdf:application/pdf;Snapshot:/Users/lcneuro/Zotero/storage/4LPC9RAD/eaay2631.html:text/html","bibtex":"@article{udrescu2020,\n\ttitle = {{AI} {Feynman}: {A} physics-inspired method for symbolic regression},\n\tvolume = {6},\n\tcopyright = {Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.},\n\tissn = {2375-2548},\n\tshorttitle = {{AI} {Feynman}},\n\turl = {https://advances.sciencemag.org/content/6/16/eaay2631},\n\tdoi = {10.1126/sciadv.aay2631},\n\tabstract = {A core challenge for both physics and artificial intelligence (AI) is symbolic regression: finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions of practical interest often exhibit symmetries, separability, compositionality, and other simplifying properties. In this spirit, we develop a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques. We apply it to 100 equations from the Feynman Lectures on Physics, and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult physics-based test set, we improve the state-of-the-art success rate from 15 to 90\\%.\nOur physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers.\nOur physics-inspired algorithm for symbolic regression is able to discover complex physics equations from mere tables of numbers.},\n\tlanguage = {en},\n\tnumber = {16},\n\turldate = {2020-04-23},\n\tjournal = {Science Advances},\n\tauthor = {Udrescu, Silviu-Marian and Tegmark, Max},\n\tmonth = apr,\n\tyear = {2020},\n\tnote = {Publisher: American Association for the Advancement of Science\nSection: Research Article},\n\tkeywords = {david, neuroblox: scientific ML},\n\tpages = {eaay2631},\n\tfile = {Full Text PDF:/Users/lcneuro/Zotero/storage/D3IWBJCH/Udrescu and Tegmark - 2020 - AI Feynman A physics-inspired method for symbolic.pdf:application/pdf;Snapshot:/Users/lcneuro/Zotero/storage/4LPC9RAD/eaay2631.html:text/html},\n}\n\n","author_short":["Udrescu, S.","Tegmark, M."],"bibbaseid":"udrescu-tegmark-aifeynmanaphysicsinspiredmethodforsymbolicregression-2020","role":"author","urls":{"Paper":"https://advances.sciencemag.org/content/6/16/eaay2631"},"keyword":["david","neuroblox: scientific ML"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/f/8yBxW5neHauDryu9w/LCNeuro Site.bib","dataSources":["rQFxZQs78YQJ9m34s","ZHHpjMFTPYP8NqJif"],"keywords":["david","neuroblox: scientific ml"],"search_terms":["feynman","physics","inspired","method","symbolic","regression","udrescu","tegmark"],"title":"AI Feynman: A physics-inspired method for symbolic regression","year":2020}