Literature DB >> 32426452

AI Feynman: A physics-inspired method for symbolic regression.

Silviu-Marian Udrescu1, Max Tegmark1,2.   

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%.
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).

Entities:  

Year:  2020        PMID: 32426452      PMCID: PMC7159912          DOI: 10.1126/sciadv.aay2631

Source DB:  PubMed          Journal:  Sci Adv        ISSN: 2375-2548            Impact factor:   14.136


  5 in total

1.  Automated refinement and inference of analytical models for metabolic networks.

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

2.  Distilling free-form natural laws from experimental data.

Authors:  Michael Schmidt; Hod Lipson
Journal:  Science       Date:  2009-04-03       Impact factor: 47.728

3.  Sparse identification of nonlinear dynamics for rapid model recovery.

Authors:  Markus Quade; Markus Abel; J Nathan Kutz; Steven L Brunton
Journal:  Chaos       Date:  2018-06       Impact factor: 3.642

4.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems.

Authors:  Steven L Brunton; Joshua L Proctor; J Nathan Kutz
Journal:  Proc Natl Acad Sci U S A       Date:  2016-03-28       Impact factor: 11.205

5.  Toward an artificial intelligence physicist for unsupervised learning.

Authors:  Tailin Wu; Max Tegmark
Journal:  Phys Rev E       Date:  2019-09       Impact factor: 2.529

  5 in total
  13 in total

1.  Knowledge extraction and transfer in data-driven fracture mechanics.

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

2.  Latent space of a small genetic network: Geometry of dynamics and information.

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

3.  Data-driven discovery of the governing equations of dynamical systems via moving horizon optimization.

Authors:  Fernando Lejarza; Michael Baldea
Journal:  Sci Rep       Date:  2022-07-12       Impact factor: 4.996

4.  Learning transport processes with machine intelligence.

Authors:  Francesco Miniati; Gianluca Gregori
Journal:  Sci Rep       Date:  2022-07-09       Impact factor: 4.996

5.  Gauss curvature-based unique signatures of individual large earthquakes and its implications for customized data-driven prediction.

Authors:  In Ho Cho
Journal:  Sci Rep       Date:  2022-05-23       Impact factor: 4.996

6.  Comparing data driven and physics inspired models for hopping transport in organic field effect transistors.

Authors:  Madhavkrishnan Lakshminarayanan; Rajdeep Dutta; D V Maheswar Repaka; Senthilnath Jayavelu; Wei Lin Leong; Kedar Hippalgaonkar
Journal:  Sci Rep       Date:  2021-12-08       Impact factor: 4.379

7.  Data-driven discovery of Green's functions with human-understandable deep learning.

Authors:  Nicolas Boullé; Christopher J Earls; Alex Townsend
Journal:  Sci Rep       Date:  2022-03-22       Impact factor: 4.379

8.  Capturing functional relations in fluid-structure interaction via machine learning.

Authors:  Tejas Soni; Ashwani Sharma; Rajdeep Dutta; Annwesha Dutta; Senthilnath Jayavelu; Saikat Sarkar
Journal:  R Soc Open Sci       Date:  2022-04-06       Impact factor: 2.963

9.  Machine learning of material properties: Predictive and interpretable multilinear models.

Authors:  Alice E A Allen; Alexandre Tkatchenko
Journal:  Sci Adv       Date:  2022-05-06       Impact factor: 14.957

10.  Combining symbolic regression with the Cox proportional hazards model improves prediction of heart failure deaths.

Authors:  Casper Wilstrup; Chris Cave
Journal:  BMC Med Inform Decis Mak       Date:  2022-07-25       Impact factor: 3.298

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.