AI Feynman: a Physics-Inspired Method for Symbolic Regression. Udrescu, S. & Tegmark, M. arXiv:1905.11481 [hep-th, physics:physics], May, 2019. arXiv: 1905.11481Paper abstract bibtex A core challenge for both physics and artificial intellicence (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 test set, we improve the state of the art success rate from 15% to 90%.
@article{udrescu_ai_2019,
title = {{AI} {Feynman}: a {Physics}-{Inspired} {Method} for {Symbolic} {Regression}},
shorttitle = {{AI} {Feynman}},
url = {http://arxiv.org/abs/1905.11481},
abstract = {A core challenge for both physics and artificial intellicence (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 test set, we improve the state of the art success rate from 15\% to 90\%.},
urldate = {2019-06-01},
journal = {arXiv:1905.11481 [hep-th, physics:physics]},
author = {Udrescu, Silviu-Marian and Tegmark, Max},
month = may,
year = {2019},
note = {arXiv: 1905.11481},
keywords = {Computer Science - Artificial Intelligence, Physics - Computational Physics, high energy physics, machine learning, mentions sympy, symbolic regression},
}
Downloads: 0
{"_id":"idwN9FutEuud4JNdG","bibbaseid":"udrescu-tegmark-aifeynmanaphysicsinspiredmethodforsymbolicregression-2019","authorIDs":[],"author_short":["Udrescu, S.","Tegmark, M."],"bibdata":{"bibtype":"article","type":"article","title":"AI Feynman: a Physics-Inspired Method for Symbolic Regression","shorttitle":"AI Feynman","url":"http://arxiv.org/abs/1905.11481","abstract":"A core challenge for both physics and artificial intellicence (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 test set, we improve the state of the art success rate from 15% to 90%.","urldate":"2019-06-01","journal":"arXiv:1905.11481 [hep-th, physics:physics]","author":[{"propositions":[],"lastnames":["Udrescu"],"firstnames":["Silviu-Marian"],"suffixes":[]},{"propositions":[],"lastnames":["Tegmark"],"firstnames":["Max"],"suffixes":[]}],"month":"May","year":"2019","note":"arXiv: 1905.11481","keywords":"Computer Science - Artificial Intelligence, Physics - Computational Physics, high energy physics, machine learning, mentions sympy, symbolic regression","bibtex":"@article{udrescu_ai_2019,\n\ttitle = {{AI} {Feynman}: a {Physics}-{Inspired} {Method} for {Symbolic} {Regression}},\n\tshorttitle = {{AI} {Feynman}},\n\turl = {http://arxiv.org/abs/1905.11481},\n\tabstract = {A core challenge for both physics and artificial intellicence (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 test set, we improve the state of the art success rate from 15\\% to 90\\%.},\n\turldate = {2019-06-01},\n\tjournal = {arXiv:1905.11481 [hep-th, physics:physics]},\n\tauthor = {Udrescu, Silviu-Marian and Tegmark, Max},\n\tmonth = may,\n\tyear = {2019},\n\tnote = {arXiv: 1905.11481},\n\tkeywords = {Computer Science - Artificial Intelligence, Physics - Computational Physics, high energy physics, machine learning, mentions sympy, symbolic regression},\n}\n\n","author_short":["Udrescu, S.","Tegmark, M."],"key":"udrescu_ai_2019","id":"udrescu_ai_2019","bibbaseid":"udrescu-tegmark-aifeynmanaphysicsinspiredmethodforsymbolicregression-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1905.11481"},"keyword":["Computer Science - Artificial Intelligence","Physics - Computational Physics","high energy physics","machine learning","mentions sympy","symbolic regression"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/nicoguaro/525293","creationDate":"2020-01-27T02:13:33.885Z","downloads":0,"keywords":["computer science - artificial intelligence","physics - computational physics","high energy physics","machine learning","mentions sympy","symbolic regression"],"search_terms":["feynman","physics","inspired","method","symbolic","regression","udrescu","tegmark"],"title":"AI Feynman: a Physics-Inspired Method for Symbolic Regression","year":2019,"dataSources":["YtBDXPDiQEyhyEDZC","fhHfrQgj3AaGp7e9E","qzbMjEJf5d9Lk78vE","45tA9RFoXA9XeH4MM","MeSgs2KDKZo3bEbxH","nSXCrcahhCNfzvXEY","ecatNAsyr4f2iQyGq","tpWeaaCgFjPTYCjg3"]}