Discovering causal relations and equations from data

G Camps-Valls, A Gerhardus, U Ninad, G Varando… - Physics Reports, 2023 - Elsevier
Physics is a field of science that has traditionally used the scientific method to answer
questions about why natural phenomena occur and to make testable models that explain the …

Artificial intelligence in physical sciences: Symbolic regression trends and perspectives

D Angelis, F Sofos, TE Karakasidis - Archives of Computational Methods …, 2023 - Springer
Symbolic regression (SR) is a machine learning-based regression method based on genetic
programming principles that integrates techniques and processes from heterogeneous …

Interpretable machine learning for science with PySR and SymbolicRegression. jl

M Cranmer - arxiv preprint arxiv:2305.01582, 2023 - arxiv.org
PySR is an open-source library for practical symbolic regression, a type of machine learning
which aims to discover human-interpretable symbolic models. PySR was developed to …

[HTML][HTML] Contemporary symbolic regression methods and their relative performance

W La Cava, B Burlacu, M Virgolin… - Advances in neural …, 2021 - ncbi.nlm.nih.gov
Many promising approaches to symbolic regression have been presented in recent years,
yet progress in the field continues to suffer from a lack of uniform, robust, and transparent …

Kan: Kolmogorov-arnold networks

Z Liu, Y Wang, S Vaidya, F Ruehle, J Halverson… - arxiv preprint arxiv …, 2024 - arxiv.org
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold
Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs …

Kan 2.0: Kolmogorov-arnold networks meet science

Z Liu, P Ma, Y Wang, W Matusik, M Tegmark - arxiv preprint arxiv …, 2024 - arxiv.org
A major challenge of AI+ Science lies in their inherent incompatibility: today's AI is primarily
based on connectionism, while science depends on symbolism. To bridge the two worlds …

Simulation intelligence: Towards a new generation of scientific methods

A Lavin, D Krakauer, H Zenil, J Gottschlich… - arxiv preprint arxiv …, 2021 - arxiv.org
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

A unified framework for deep symbolic regression

M Landajuela, CS Lee, J Yang… - Advances in …, 2022 - proceedings.neurips.cc
The last few years have witnessed a surge in methods for symbolic regression, from
advances in traditional evolutionary approaches to novel deep learning-based systems …

Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws

W Tenachi, R Ibata, FI Diakogiannis - The Astrophysical Journal, 2023 - iopscience.iop.org
Symbolic regression (SR) is the study of algorithms that automate the search for analytic
expressions that fit data. While recent advances in deep learning have generated renewed …

Combining data and theory for derivable scientific discovery with AI-Descartes

C Cornelio, S Dash, V Austel, TR Josephson… - Nature …, 2023 - nature.com
Scientists aim to discover meaningful formulae that accurately describe experimental data.
Mathematical models of natural phenomena can be manually created from domain …