Back to the catalog
Software — free catalog
Sequential Monte Carlo-based Symbolic Regression (SMC-SR)
A NASA software catalog entry available for reuse or request.
About this technology
Overview
Sequential Monte Carlo-based Symbolic Regression (SMC-SR) is a software that performs symbolic regression, a prevalent interpretable machine learning technique, to estimate mathematical equations from data. The software requires labeled numerical data, representing inputs and their corresponding outputs, to learn a symbolic relationship between them. This data can be provided in common formats like CSV files or arrays. The software outputs a family of strings, each representing a symbolic expression, which together form a probability distribution over models conditioned on the data. The software is intended for research use only.