Learning Operators with Mesh-Informed Neural Networks

by   Nicola Rares Franco, et al.

Thanks to their universal approximation properties and new efficient training strategies, Deep Neural Networks are becoming a valuable tool for the approximation of mathematical operators. In the present work, we introduce Mesh-Informed Neural Networks (MINNs), a class of architectures specifically tailored to handle mesh based functional data, and thus of particular interest for reduced order modeling of parametrized Partial Differential Equations (PDEs). The driving idea behind MINNs is to embed hidden layers into discrete functional spaces of increasing complexity, obtained through a sequence of meshes defined over the underlying spatial domain. The approach leads to a natural pruning strategy which enables the design of sparse architectures that are able to learn general nonlinear operators. We assess this strategy through an extensive set of numerical experiments, ranging from nonlocal operators to nonlinear diffusion PDEs, where MINNs are compared to classical fully connected Deep Neural Networks. Our results show that MINNs can handle functional data defined on general domains of any shape, while ensuring reduced training times, lower computational costs, and better generalization capabilities, thus making MINNs very well-suited for demanding applications such as Reduced Order Modeling and Uncertainty Quantification for PDEs.



page 16


Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data

What do data tell us about physics-and what don't they tell us? There ha...

A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations

Within the framework of parameter dependent PDEs, we develop a construct...

SPINN: Sparse, Physics-based, and Interpretable Neural Networks for PDEs

We introduce a class of Sparse, Physics-based, and Interpretable Neural ...

DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

While it is widely known that neural networks are universal approximator...

U-NO: U-shaped Neural Operators

Neural operators generalize classical neural networks to maps between in...

Connections between Numerical Algorithms for PDEs and Neural Networks

We investigate numerous structural connections between numerical algorit...

Physics-informed Neural Networks-based Model Predictive Control for Multi-link Manipulators

We discuss nonlinear model predictive control (NMPC) for multi-body dyna...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.