Unsupervised Deep Learning Algorithm for PDE-based Forward and Inverse Problems
Machine Learning
2019-04-12 v1 Machine Learning
Abstract
We propose a neural network-based algorithm for solving forward and inverse problems for partial differential equations in unsupervised fashion. The solution is approximated by a deep neural network which is the minimizer of a cost function, and satisfies the PDE, boundary conditions, and additional regularizations. The method is mesh free and can be easily applied to an arbitrary regular domain. We focus on 2D second order elliptical system with non-constant coefficients, with application to Electrical Impedance Tomography.
Cite
@article{arxiv.1904.05417,
title = {Unsupervised Deep Learning Algorithm for PDE-based Forward and Inverse Problems},
author = {Leah Bar and Nir Sochen},
journal= {arXiv preprint arXiv:1904.05417},
year = {2019}
}
Comments
15 pages, 11 figures