DeepAI AI Chat
Log In Sign Up

Neural network guided adjoint computations in dual weighted residual error estimation

by   Julian Roth, et al.

In this work, we are concerned with neural network guided goal-oriented a posteriori error estimation and adaptivity using the dual weighted residual method. The primal problem is solved using classical Galerkin finite elements. The adjoint problem is solved in strong form with a feedforward neural network using two or three hidden layers. The main objective of our approach is to explore alternatives for solving the adjoint problem with greater potential of a numerical cost reduction. The proposed algorithm is based on the general goal-oriented error estimation theorem including both linear and nonlinear stationary partial differential equations and goal functionals. Our developments are substantiated with some numerical experiments that include comparisons of neural network computed adjoints and classical finite element solutions of the adjoints. In the programming software, the open-source library deal.II is successfully coupled with LibTorch, the PyTorch C++ application programming interface.


page 14

page 16

page 17


Multigoal-oriented dual-weighted-residual error estimation using deep neural networks

Deep learning has shown successful application in visual recognition and...

Goal-Oriented A Posteriori Error Estimation for the Biharmonic Problem Based on Equilibrated Moment Tensor

In this article, goal-oriented a posteriori error estimation for the bih...

An MP-DWR method for h-adaptive finite element methods

In a dual weighted residual based adaptive finite element method for sol...

Goal-oriented adaptive mesh refinement for non-symmetric functional settings

In this article, a Petrov-Galerkin duality theory is developed. This the...

Multigoal-oriented error estimation and mesh adaptivity for fluid-structure interaction

In this work, we consider multigoal-oriented error estimation for statio...