AI Descartes: Combining Data and Theory for Derivable Scientific Discovery

Abstract

Scientists have long aimed to discover meaningful formulae which accurately describe experimental data. One common approach is to manually create mathematical models of natural phenomena using domain knowledge, then fit these models to data. In contrast, machine-learning algorithms automate the construction of accurate data-driven models while consuming large amounts of data. Ensuring that such models are consistent with existing knowledge is an open problem. We develop a method for combining logical reasoning with symbolic regression, enabling principled derivations of models of natural phenomena. We demonstrate these concepts for Kepler's third law of planetary motion, Einstein's relativistic time-dilation law, and Langmuir's theory of adsorption, automatically connecting experimental data with background theory in each case. We show that laws can be discovered from few data points when using formal logical reasoning to distinguish the correct formula from a set of plausible formulas that have similar error on the data. The combination of reasoning with machine learning provides generalizable insights into key aspects of natural phenomena. We envision that this combination will enable derivable discovery of fundamental laws of science. We believe that this is a crucial first step for connecting the missing links in automating the scientific method.