AI Feynman: A physics-inspired method for symbolic regression
© 2020 The Authors. 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 symmetrie...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/132379 |
| _version_ | 1826192162429075456 |
|---|---|
| author | Udrescu, Silviu-Marian Tegmark, Max |
| author_facet | Udrescu, Silviu-Marian Tegmark, Max |
| author_sort | Udrescu, Silviu-Marian |
| collection | MIT |
| description | © 2020 The Authors. 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%. |
| first_indexed | 2024-09-23T09:07:11Z |
| format | Article |
| id | mit-1721.1/132379 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:07:11Z |
| publishDate | 2021 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | dspace |
| spelling | mit-1721.1/1323792021-09-21T03:59:52Z AI Feynman: A physics-inspired method for symbolic regression Udrescu, Silviu-Marian Tegmark, Max © 2020 The Authors. 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%. 2021-09-20T18:22:07Z 2021-09-20T18:22:07Z 2020-11-09T19:29:37Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/132379 en 10.1126/SCIADV.AAY2631 Science Advances Creative Commons Attribution NonCommercial License 4.0 https://creativecommons.org/licenses/by-nc/4.0/ application/pdf American Association for the Advancement of Science (AAAS) Science Advances |
| spellingShingle | Udrescu, Silviu-Marian Tegmark, Max AI Feynman: A physics-inspired method for symbolic regression |
| title | AI Feynman: A physics-inspired method for symbolic regression |
| title_full | AI Feynman: A physics-inspired method for symbolic regression |
| title_fullStr | AI Feynman: A physics-inspired method for symbolic regression |
| title_full_unstemmed | AI Feynman: A physics-inspired method for symbolic regression |
| title_short | AI Feynman: A physics-inspired method for symbolic regression |
| title_sort | ai feynman a physics inspired method for symbolic regression |
| url | https://hdl.handle.net/1721.1/132379 |
| work_keys_str_mv | AT udrescusilviumarian aifeynmanaphysicsinspiredmethodforsymbolicregression AT tegmarkmax aifeynmanaphysicsinspiredmethodforsymbolicregression |