https://github.com/Miyazaki-Yu/ecnn4klm

https://github.com/Miyazaki-Yu/ecnn4klm

Last synced: 14 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/Miyazaki-Yu/ecnn4klm
• Owner: Miyazaki-Yu
• License: mit
• Created: 2023-05-03T11:22:31.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-10-11T13:47:22.000Z (about 1 year ago)
• Last Synced: 2024-08-01T16:53:13.048Z (3 months ago)
• Language: Python
• Size: 35.3 MB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# ecnn4klm: Equivariant Convolutional Neural Network for Kondo Lattice Model

`ecnn4klm` aims to perform fast and large-scale simulations of localized spin dynamics in the Kondo lattice model using an equivariant convolutional neural network (ECNN). For details on the ECNN model, please refer to the paper: Y. Miyazaki, Mach. Learn.: Sci. Technol. 4 045006 (2023).

## Installation

`ecnn4klm` is based on PyTorch and e3nn. To install, you need PyTorch version 1.8 or higher. I also highly recommend running it on a GPU to maximize performance.

```bash

pip install git+https://github.com/Miyazaki-Yu/ecnn4klm.git

```

## Brief Introduction with Colab

You can easily try it out on your browser using Google Colab.

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://colab.research.google.com/github/Miyazaki-Yu/ecnn4klm/blob/master/notebook/ecnn_test.ipynb)

## Data

The models and the datasets for both the square lattice and the triangular lattice cases, which are discussed in the paper, can be found in the [`data/`](https://github.com/Miyazaki-Yu/ecnn4klm/tree/main/data) directory.

## How to Cite

```bibtex

@article{Miyazaki2023_ecnn4klm,

doi = {10.1088/2632-2153/acffa2},

url = {https://dx.doi.org/10.1088/2632-2153/acffa2},

year = {2023},

month = {oct},

publisher = {IOP Publishing},

volume = {4},

number = {4},

pages = {045006},

author = {Yu Miyazaki},

title = {Equivariant neural networks for spin dynamics simulations of itinerant magnets},

journal = {Machine Learning: Science and Technology},

}

```