# AI Feynman: a Physics-Inspired Method for Symbolic Regression

## TL;DR

This paper introduces a physics-inspired recursive algorithm for symbolic regression that effectively discovers symbolic expressions from data, significantly outperforming previous methods on challenging physics equations.

## Contribution

It presents a novel recursive multidimensional symbolic regression method combining neural networks and physics-inspired techniques, achieving higher success rates on complex equations.

## Key findings

- Successfully discovered all equations from the Feynman Lectures
- Improved success rate on difficult equations from 15% to 90%
- Outperformed existing software on benchmark tests

## Abstract

A core challenge for both physics and artificial intellicence (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 test set, we improve the state of the art success rate from 15% to 90%.