This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyTorch. This package offers three main features: (i) dimensionality reduction, (ii) clustering, and (iii) friendly data visualization. It relies on a PyTorch backend, enabling (i) fast and efficient training of SOMs through GPU acceleration, and (ii) easy and scalable integrations with PyTorch ecosystem. Moreover, torchsom follows the scikit-learn API for ease of use and extensibility. The library is released under the Apache 2.0 license with 90% test coverage, and its source code and documentation are available at https://github.com/michelin/TorchSOM.
Cite
@article{arxiv.2510.11147,
title = {torchsom: The Reference PyTorch Library for Self-Organizing Maps},
author = {Louis Berthier and Ahmed Shokry and Maxime Moreaud and Guillaume Ramelet and Eric Moulines},
journal= {arXiv preprint arXiv:2510.11147},
year = {2025}
}
Comments
4 mains pages with 2 tables, 4 pages of references, 15 pages of appendices with 13 figures and 3 tables