GMLS-Nets: A framework for learning from unstructured data

arXiv1909.05371MaRDI QIDQ6325125

Author name not available (Why is that?)

Publication date: 6 September 2019

Abstract: Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a non-parametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications.

Has companion code repository: https://github.com/rgp62/gmls-nets

This page was built for publication: GMLS-Nets: A framework for learning from unstructured data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6325125)