sonicjh Goto Github PK

conservative_pinns

We propose a conservative physics-informed neural network (cPINN) on decompose domains for nonlinear conservation laws. The conservation property of cPINN is obtained by enforcing the flux continuity in the strong form along the sub-domain interfaces.

deep-ritz-method3

Reproduce the first two numerical experiments(Pytorch)

deeponet

Learning nonlinear operators via DeepONet

deeponet-fno

DeepONet & FNO (with practical extensions)

deepritz2

Implementation of the Deep Ritz method and the Deep Galerkin method

deepritzmethod

Group project for Deep Learning: Algorithms and Applications in Peking University 2018 Spring. This is a brief survey, discussion and implementation for deep Ritz method.

deepxde

A library for scientific machine learning and physics-informed learning

first

test

gaussian-process-regression

高斯过程回归

mionet

MIONet: Learning multiple-input operators via tensor product

modulus

A PyTorch based deep-learning toolkit for developing DL models for physical systems

mopso

多目标粒子群算法简单实现

mopso_python

based on the version of "https://github.com/dreamoffeature/mopso", which has too many mistakes, I rewrite the MOPSO algorithm

neural-pde-solver

physics-informed-deeponets

pytorch-gan

PyTorch implementations of Generative Adversarial Networks.