The FASP package is designed for developing and testing new efficient solvers and preconditioners for discrete partial differential equations (PDEs) or systems of PDEs. The main components of the p…

fast randomized SVD and its application to SVT algorithm

randomized QB factorization for fixed-precision low-rank matrix approximation

A collection listing all Achievements available on the GitHub profile 🏆

相当不错的图书，例如《数学之美》、《浪潮之巅》、《TCP/IP卷一/卷二/卷三》等；一些大的上传受限制的文件《图解TCP_IP_第5版》、《深入理解Java虚拟机JVM》、《effective java》等在README

[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax for Partial Differential Equations

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning (NeurIPS 2020)

Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations

Neural network based solvers for partial differential equations and inverse problems 🌌. Implementation of physics-informed neural networks in pytorch.

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

DiffNet: A FEM based neural PDE solver package

Fourier Neural Operators to solve for Allen Cahn PDE equations

Learning with Higher Expressive Power than Neural Networks (On Learning PDEs)

Repo to the paper "Message Passing Neural PDE Solvers"

Solving High Dimensional Partial Differential Equations with Deep Neural Networks

Neural Stochastic PDEs: resolution-invariant modelling of continuous spatiotemporal dynamics

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs

Physics-constrained auto-regressive convolutional neural networks for dynamical PDEs

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Reference implementation of Finite Element Networks as proposed in "Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks" at ICLR 2022

Using graph network to solve PDEs

Learning in infinite dimension with neural operators.