What is it about?
A friendly and complete introduction to data-driven equation discovery, also known as Symbolic Regression. This AI tool is mainly focused to automate discovery in the natural sciences and learn interpretable models. The state-of-the-art of this topic is presented and current limitations and challenges.
Featured Image
Photo by ThisisEngineering on Unsplash
Why is it important?
The application of symbolic regression to real-world and scientific problems is crucial to test the credibility of SR as a scientific discovery tool and emphasize its limitations.
Perspectives
Symbolic regression is an old topic that dates back to the 16th century and was used by J.Kepler in the discovery of its third law. Folowing the big data revolution, SR's approaches have significantly evolved and uses state-of-the-art machine learning techniques such as transformers and LLMs.
Nour Makke
Read the Original
This page is a summary of: Interpretable scientific discovery with symbolic regression: a review, Artificial Intelligence Review, January 2024, Springer Science + Business Media,
DOI: 10.1007/s10462-023-10622-0.
You can read the full text:
Resources
Contributors
The following have contributed to this page
