Skip to content

We use Neural Quantum States (NQS) to predict bound-state properties of various quantum systems

License

Notifications You must be signed in to change notification settings

javier-rozalen/ml-tools-for-qm

Repository files navigation

Machine learning tools to solve the Schrödinger equation

Fancy Neural Network

What is this repository?

It contains the code referred to in this article. The repository is meant to provide a detailed PyTorch implementation of the method of Neural Quantum States for three different quantum systems, as a first resource for teaching purposes and also as a guide for those starting in the field.

Repository structure:

.
├── assets/                                  # Images, logos
├── .gitignore
├── 1_harmonic_oscillator.ipynb               # NQS implementation of a quantum HO
├── 2_double_well.ipynb                       # NQS implementation of a quantum double well
├── 3_hydrogen_atom.ipynb                     # NQS implementation of a hydrogenoid atom
├── CITATION.cff                              # Citation file
├── LICENSE                                   # License
├── README.md
├── env.yml                                   # Conda environment
└── requirements.txt                          # requirements

Installation

To install this project in your computer, choose one of the following options:

Option 1. conda anaconda

  1. Clone the repository:

git clone https://github.com/javier-rozalen/ml-tools-for-qm.git && cd ml-tools-for-qm

  1. If conda is not installed in your system, you can download it from https://docs.conda.io/en/latest/miniconda.html.
  2. Create a conda environment from the .yml file in the repository:

conda env create -f env.yml

  1. Activate the environment:

conda activate ml-tools-for-qm

  1. Install further requirements:

pip install -r requirements.txt

Option 2. Docker anaconda

Coming soon...

Usage

There are three code files:

  • 1_harmonic_oscillator.ipynb
  • 2_double_well.ipynb
  • 3_hydrogen_atom.ipynb

They are all in the .ipynb format, designed to be open with Jupyter Notebook. To open each of them, run the command jupyter notebook file.ipynb, "file" being one of the three scripts in the list above. Each cell cell has been pre-run, so you should be able to see the outputs from the start, even before running the cells. Below is a demo of the first file being run:

Uninstall

To remove the virtual environment created with Option 1 follow the steps below:

  1. Make sure your current environment is not ml-tools-for-qm, or if it is, type:

conda deactivate

  1. Remove the environment.

conda remove -n ml-tools-for-qm --all

  1. Remove the local repository.

Windows: rmdir /S ml-tools-for-qm

Linux/MacOS: rm -r ml-tools-for-qm

Support

If you have any questions or issues, please contact us at jrozalen@ub.edu.

About

We use Neural Quantum States (NQS) to predict bound-state properties of various quantum systems

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published