Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives
Искусственный интеллект в физических науках: тенденции и перспективы символьной регрессии
2023-04-19
SCID: 54.1/3wr2d85d
Discuss with AI
analytical equationsgenetic programmingmachine learningphysical sciencessymbolic regression
Figures from the paper
Abstract (AI)
Symbolic regression (SR) is a machine learning-based regression method based on genetic programming principles that integrates techniques and processes from heterogeneous scientific fields and is capable of providing analytical equations purely from data. This remarkable characteristic diminishes the need to incorporate prior knowledge about the investigated system. SR can spot profound and elucidate ambiguous relations that can be generalizable, applicable, explainable and span over most scientific, technological, economical, and social principles. In this review, current state of the art is documented, technical and physical characteristics of SR are presented, the available programming techniques are investigated, fields of application are explored, and future perspectives are discussed. Supplementary Information: The online version contains supplementary material available at 10.1007/s11831-023-09922-z.
Key Findings
1
By producing explicit equations, symbolic regression reduces the need for prior knowledge about the investigated physical system.
2
Symbolic regression can identify and clarify complex relationships that may be generalizable, applicable, and explainable across diverse scientific and technological domains.
3
Symbolic regression uses machine-learning and genetic-programming principles to derive analytical equations directly from data.
4
The review surveys symbolic regression’s current state of the art, technical and physical characteristics, programming techniques, application fields, and future perspectives.
Research Object
symbolic regression (SR) applied to physical-science systems and data
Research Subject
the technical and physical characteristics, programming techniques, application fields, and future perspectives of SR
Publication Details
Publication Date
2023-04-19
Journal
Publisher
ISSN
Cited by
242
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies2015
Materials discovery and design using machine learning2017
Machine learning in materials science2019