Popular GitHub Repositories for Numerical Methods

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

PyDEns is a framework for solving Ordinary and Partial Differential Equations (ODEs & PDEs) using neural networks

Code for: "Neural Rough Differential Equations for Long Time Series", (ICML 2021)

This repository contains code released by DiffEqML Research

Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021

This a JavaScript Library for the Numerical Javascript and Machine Learning

Web app for numerical interpolation with graphing. Built with React, Vite, Tailwind, and SCSS.

A pytorch framework for solving PDEs via Physics Informed Neural Networks (PINNs)!

基于 scikit-learn 的非线性回归

Interpolation, linear equations, least squared, eigenvalues, ode, quadratures, roots, minimization, Monte-Carlo, neural networks

Adaptive quadratures for nonlinear approximation of low-dimensional PDEs using smooth neural networks

[NeurIPS 2024] Official PyTorch implementation for the paper "AdjointDEIS: Efficient Gradients for Diffusion Models"

这个项目使用序列二次规划（SQP）结合内点法实现了一种数值优化算法，用于生成针对给定模型的对抗样本。

neural-network-based ROM testbed using an auto-encoder as an approximation manifold for the state, and an MLP for the reduced residual function