Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems

Perez, Sarah; Maddu, Suryanarayana; F. Sbalzarini, Ivo; Poncet, Philippe

doi:10.1016/j.jcp.2023.112342

Public

Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems

Shared by NobleBlocks on Jul 7, 2023 • 12:00 AM UTC

Authors:

Sarah Perez

Suryanarayana Maddu

Ivo F. Sbalzarini

Abstract

In this paper, we present a novel methodology for automatic adaptive weighting of Bayesian Physics-Informed Neural Networks (BPINNs), and we demonstrate that this makes it possible to robustly address multi-objective and multiscale problems. BPINNs are a popular framework for data assimilation, comb...

Subject

Weighting

Bayesian probability

Artificial neural network

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!