KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #typescript #developer-tools #claude-code #ai-agent #codex #deepseek-harness #ai-agents #cli #react #mcp

SCALE-PINN

★ 30 Open GitHub ↗

Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Scale-PINN

[![python >3.8](https://img.shields.io/badge/python-3.8-brightgreen)](https://www.python.org/)

## **Learning Efficient Physics-Informed Neural Networks Through Sequential Correction**

__Pao-Hsiung Chiu, Jian Cheng Wong, Chin Chun Ooi, Chang Wei, Yuchen Fan, Yew-Soon Ong__

# Install
[![jax-0.4.33](https://img.shields.io/badge/jax-0.4.33-yellowgreen)](https://github.com/google/jax) [![evojax-0.2.17](https://img.shields.io/badge/evojax-0.2.17-orange)](https://github.com/google/evojax) [![evosax-0.1.6](https://img.shields.io/badge/evosax-0.1.6-red)](https://github.com/RobertTLange/evosax) [![flax-0.9.0](https://img.shields.io/badge/flax-0.9.0-lightgrey)](https://github.com/google/flax) [![optax-0.2.3](https://img.shields.io/badge/optax-0.2.3-blue)](https://github.com/google-deepmind/optax) [![numpy-2.1.1](https://img.shields.io/badge/numpy-2.1.1-green)](https://github.com/numpy/numpy) [![pandas-2.2.3](https://img.shields.io/badge/pandas-2.2.3-yellow)](https://github.com/pandas-dev/pandas) [![matplotlib-3.9.2](https://img.shields.io/badge/matplotlib-3.9.2-purple)](https://github.com/matplotlib/matplotlib)

# Usage
You can download this repo and run the demo tasks on your computing machine.

# Time cost
Typical install time should be under 30 minutes for all the above packages.

Expected time required for training in the provided scripts should be under 10 minutes on a workstation with Intel Xeon W-2275 CPU and Nvidia Gefore RTX 3090 GPU.

# Coypright

This tool is developed in Computational Sustainability (CoS) Division, Institute of High Performance Computing (IHPC), A*STAR.

The copyright holder for this project is Computational Sustainability (CoS) Division, Institute of High Performance Computing (IHPC), A*STAR.

# Citation

Pao-Hsiung Chiu, Jian Cheng Wong, Chin Chun Ooi, Chang Wei, Yuchen Fan, Yew-Soon Ong, _"Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction"_. https://arxiv.org/abs/2602.19475

SCALE-PINN

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README