What is it about?
Using data from high-energy physics, AI re-discovers the underlying physical mechanism that explains how particles are formed in the universe. This proves that scientific discovery could be automated in the era of AI. In this report, symbolic regression, a branch of AI, is used to infer a mathematical expression, i.e., an interpretable model, that explains the underlying physical process.
Featured Image
Photo by Dan Cristian Pădureț on Unsplash
Why is it important?
This is among the first evidence of automating scientific discovery through AI, namely, symbolic regression, using data collected in an experiment at CERN. Most of symbolic regression applications make use of synthetic data.
Perspectives
This is an example to follow for the successful application of AI to learn physical models from experimental, noisy data.
Nour Makke
Read the Original
This page is a summary of: Inferring interpretable models of fragmentation functions using symbolic regression, Machine Learning Science and Technology, April 2025, Institute of Physics Publishing,
DOI: 10.1088/2632-2153/adb3ec.
You can read the full text:
Resources
Contributors
The following have contributed to this page
