Back to Search Start Over

Spectral-Bias and Kernel-Task Alignment in Physically Informed Neural Networks

Authors :
Seroussi, Inbar
Miron, Asaf
Ringel, Zohar
Publication Year :
2023

Abstract

Physically informed neural networks (PINNs) are a promising emerging method for solving differential equations. As in many other deep learning approaches, the choice of PINN design and training protocol requires careful craftsmanship. Here, we suggest a comprehensive theoretical framework that sheds light on this important problem. Leveraging an equivalence between infinitely over-parameterized neural networks and Gaussian process regression (GPR), we derive an integro-differential equation that governs PINN prediction in the large data-set limit -- the neurally-informed equation. This equation augments the original one by a kernel term reflecting architecture choices and allows quantifying implicit bias induced by the network via a spectral decomposition of the source term in the original differential equation.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2307.06362
Document Type :
Working Paper