KP-PINNs: Kernel Packet Accelerated Physics Informed Neural Networks
By: Siyuan Yang , Cheng Song , Zhilu Lai and more
Potential Business Impact:
Solves hard math problems more reliably.
Differential equations are involved in modeling many engineering problems. Many efforts have been devoted to solving differential equations. Due to the flexibility of neural networks, Physics Informed Neural Networks (PINNs) have recently been proposed to solve complex differential equations and have demonstrated superior performance in many applications. While the L2 loss function is usually a default choice in PINNs, it has been shown that the corresponding numerical solution is incorrect and unstable for some complex equations. In this work, we propose a new PINNs framework named Kernel Packet accelerated PINNs (KP-PINNs), which gives a new expression of the loss function using the reproducing kernel Hilbert space (RKHS) norm and uses the Kernel Packet (KP) method to accelerate the computation. Theoretical results show that KP-PINNs can be stable across various differential equations. Numerical experiments illustrate that KP-PINNs can solve differential equations effectively and efficiently. This framework provides a promising direction for improving the stability and accuracy of PINNs-based solvers in scientific computing.
Similar Papers
Physics-Informed Neural Networks with Unknown Partial Differential Equations: an Application in Multivariate Time Series
Machine Learning (CS)
Finds hidden rules to predict future events.
Adaptive Physics-informed Neural Networks: A Survey
Machine Learning (CS)
Teaches computers to solve science problems faster.
Extended Interface Physics-Informed Neural Networks Method for Moving Interface Problems
Numerical Analysis
Solves tricky problems with moving parts faster.