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

Title:
torchcvnn: A PyTorch-based library to easily experiment with state-of-the-art Complex-Valued Neural Networks
Authors:
Fix, Jérémy, Gabot, Quentin, Nguyen, X. Huy, Frontera-Pons, Joana, Ren, Chengfang, Ovarlez, Jean-Philippe
Contributors:
Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Bio-Inspired, Situated and Cellular Unconventional Information Technologies (BISCUIT), Department of Complex Systems, Artificial Intelligence & Robotics (LORIA - AIS), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), CentraleSupélec, Sondra, CentraleSupélec, Université Paris-Saclay (SONDRA), ONERA-CentraleSupélec-Université Paris-Saclay, DEMR, ONERA, Université Paris Saclay [Palaiseau], ONERA-Université Paris-Saclay
Source:
International Joint Conference on Neural Networks. :1-9
Publisher Information:
CCSD; IEEE, 2025.
Publication Year:
2025
Collection:
collection:ONERA
collection:CNRS
collection:SUP_SONDRA
collection:LORIA2
collection:CENTRALESUPELEC
collection:UNIV-LORRAINE
collection:LORIA
collection:LORIA-AIS
collection:UNIV-PARIS-SACLAY
collection:UNIVERSITE-PARIS-SACLAY
collection:GS-COMPUTER-SCIENCE
collection:HUB-IA
collection:DEMR_ONERA
collection:AM2I-UL
Subject Terms:
Complex-valued artificial neural network, Signal processing, Image processing, Computer Vision and Image Processing, [INFO.INFO-TS]Computer Science [cs], Signal and Image Processing, [INFO.INFO-AI]Computer Science [cs], Artificial Intelligence [cs.AI], [INFO.INFO-CV]Computer Science [cs], Computer Vision and Pattern Recognition [cs.CV]
Subject Geographic:
Rome, Italy
Original Identifier:
HAL: hal-05235749
Document Type:
Konferenz conferenceObject<br />Conference papers
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.1109/IJCNN64981.2025.11229081
DOI:
10.1109/IJCNN64981.2025.11229081
Access URL:
https://centralesupelec.hal.science/hal-05235749
https://centralesupelec.hal.science/hal-05235749v1/document
https://centralesupelec.hal.science/hal-05235749v1/file/Quentin_Papier_IJCNN.pdf
Rights:
info:eu-repo/semantics/OpenAccess
Accession Number:
edshal.hal.05235749v1
Database:
HAL

Weitere Informationen

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}.