Silviu-Marian Udrescu1, Max Tegmark1,2. 1. Department of Physics and Center for Brains, Minds & Machines, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. 2. Theiss Research, La Jolla, CA 92037, USA.
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%.
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%.
Authors: Michael D Schmidt; Ravishankar R Vallabhajosyula; Jerry W Jenkins; Jonathan E Hood; Abhishek S Soni; John P Wikswo; Hod Lipson Journal: Phys Biol Date: 2011-08-10 Impact factor: 2.583
Authors: Xing Liu; Christos E Athanasiou; Nitin P Padture; Brian W Sheldon; Huajian Gao Journal: Proc Natl Acad Sci U S A Date: 2021-06-08 Impact factor: 11.205
Authors: Rabea Seyboldt; Juliette Lavoie; Adrien Henry; Jules Vanaret; Mariela D Petkova; Thomas Gregor; Paul François Journal: Proc Natl Acad Sci U S A Date: 2022-06-22 Impact factor: 12.779