Communication Dans Un Congrès Année : 2025

torchcvnn: A PyTorch-based library to easily experiment with state-of-the-art Complex-Valued Neural Networks

Résumé

Complex-valued neural networks (CVNN) have attracted increasing attention in recent years, although their definition dates back to the mid-20th century. Indeed, several domains naturally process complex-valued signals, such as when sensing involves the response to an electromagnetic wave, such as remote sensing, MRI, etc. These domains would benefit from breakthroughs in complex-valued neural networks (CVNNs). We believe independent contributions to CVNNs must be gathered in a single, easy-to-use library. \texttt{torchcvnn} is an effort in that direction and provides several complex-valued building blocks, allowing us to experiment with CVNNs easily. The library is available at \url{https://github.com/torchcvnn/torchcvnn} alongside examples available at \url{https://github.com/torchcvnn/examples}.

Fichier principal
Vignette du fichier
Quentin_Papier_IJCNN.pdf (3.49 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05235749 , version 1 (02-09-2025)

Licence

Identifiants

Citer

Jérémy Fix, Quentin Gabot, X. Huy Nguyen, Joana Frontera-Pons, Chengfang Ren, et al.. torchcvnn: A PyTorch-based library to easily experiment with state-of-the-art Complex-Valued Neural Networks. International Joint Conference on Neural Networks, Jun 2025, Rome, Italy. pp.1-9, ⟨10.1109/IJCNN64981.2025.11229081⟩. ⟨hal-05235749⟩
435 Consultations
244 Téléchargements

Altmetric

Partager

  • More