Some Comparisons of Neural Network Architectures For Scientific Machine Learning
Abstract
We compare several neural network architectures for approximating solutions to and solution operators for a handful of elementary 1D partial differential equations. Specifically, we examine whether residual layers offer any benefits over fully connected layers in the context of physics-informed machine learning, finding that the two perform similarly on the problems considered. We also comparet he popular DeepONet and Fourier neural operator approaches to operator learning and observe that while the two attain comparable accuracies for linear problems, the latter yields more accurate models in the presence of a simple nonlinearity.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 2023
- Accession Number
- AD1225585
Entities
People
- Javier J. Sustaita
Organizations
- Naval Postgraduate School