{"ID":2856201,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11147","arxiv_id":"2510.11147","title":"torchsom: The Reference PyTorch Library for Self-Organizing Maps","abstract":"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.","short_abstract":"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)...","url_abs":"https://arxiv.org/abs/2510.11147","url_pdf":"https://arxiv.org/pdf/2510.11147v1","authors":"[\"Louis Berthier\",\"Ahmed Shokry\",\"Maxime Moreaud\",\"Guillaume Ramelet\",\"Eric Moulines\"]","published":"2025-10-13T08:40:00Z","proceeding":"stat.ML","tasks":"[\"stat.ML\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":608322,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2856201,"paper_url":"https://arxiv.org/abs/2510.11147","paper_title":"torchsom: The Reference PyTorch Library for Self-Organizing Maps","repo_url":"https://github.com/michelin/TorchSOM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}