AI Feynman: a Physics-Inspired Method for Symbolic Regression. Udrescu, S. & Tegmark, M. arXiv:1905.11481 [hep-th, physics:physics], May, 2019. arXiv: 1905.11481
AI Feynman: a Physics-Inspired Method for Symbolic Regression [link]Paper  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, Computer Science - Machine Learning, High Energy Physics - Theory, Physics - Computational Physics, mentions sympy, symbolic regression},
}
Downloads: 0