DeepAI AI Chat
Log In Sign Up

Neuro-symbolic partial differential equation solver

by   Pouria Mistani, et al.
The Regents of the University of California

We present a highly scalable strategy for developing mesh-free neuro-symbolic partial differential equation solvers from existing numerical discretizations found in scientific computing. This strategy is unique in that it can be used to efficiently train neural network surrogate models for the solution functions and the differential operators, while retaining the accuracy and convergence properties of state-of-the-art numerical solvers. This neural bootstrapping method is based on minimizing residuals of discretized differential systems on a set of random collocation points with respect to the trainable parameters of the neural network, achieving unprecedented resolution and optimal scaling for solving physical and biological systems.


A fast, high-order numerical method for the simulation of single-excitation states in quantum optics

We consider the numerical solution of a nonlocal partial differential eq...

Data-Driven Shadowgraph Simulation of a 3D Object

In this work we propose a deep neural network based surrogate model for ...

Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks

We are interested in the approximation of partial differential equations...

Neural Networks with Cheap Differential Operators

Gradients of neural networks can be computed efficiently for any archite...

MetaFEM: A Generic FEM Solver By Meta-expressions

Current multi-physics Finite Element Method (FEM) solvers are complex sy...

Ai4EComponentLib.jl: A Component-base Model Library in Julia

Ai4EComponentLib.jl(Ai4EComponentLib) is a component-base model library ...