Al Feynman: A physics-inspired method for symbolic regression
Al Feynman: A physics-inspired method for symbolic regression
复制标题
DOI：
10.1126/sciadv.aay2631
复制
发表时间：
2020-04-01
期刊：
影响因子：
13.6
通讯作者：
Tegmark, Max
中科院分区：
文献类型：
--
作者：
Udrescu, Silviu-Marian;Tegmark, Max
物理和人工智能（Al）的核心挑战是符号回归：找到与未知函数数据匹配的符号表达式。虽然这个问题在原则上可能是np困难的，但实际的函数通常表现出对称性、可分离性、组合性和其他简化性质。本着这种精神，我们开发了一种递归多维符号回归算法，该算法将神经网络拟合与一套物理启发的技术相结合。我们将它应用于费曼物理讲座中的100个方程，它可以发现所有的方程，而以前公开的软件只能破解71个；对于更困难的基于物理的测试集，我们将最先进的成功率从15%提高到90%。
A core challenge for both physics and artificial intelligence (Al) 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 physics-based test set, we improve the state-of-the-art success rate from 15 to 90%.