Recent Advances of NeuroDiffEq -- An Open-Source Library for Physics-Informed Neural Networks
This provides a tool for researchers in physics and engineering interested in physics-informed neural networks, but it is incremental as it builds on an existing library.
The authors tackled the lack of open-source libraries for solving differential equations with neural networks by presenting recent updates to NeuroDiffEq, demonstrating its ability to handle complex boundary value problems in arbitrary dimensions, boundary conditions at infinity, and dynamic injection at runtime.
Solving differential equations is a critical challenge across a host of domains. While many software packages efficiently solve these equations using classical numerical approaches, there has been less effort in developing a library for researchers interested in solving such systems using neural networks. With PyTorch as its backend, NeuroDiffEq is a software library that exploits neural networks to solve differential equations. In this paper, we highlight the latest features of the NeuroDiffEq library since its debut. We show that NeuroDiffEq can solve complex boundary value problems in arbitrary dimensions, tackle boundary conditions at infinity, and maintain flexibility for dynamic injection at runtime.