VS2N : Interactive Dynamic Visualization ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
VS2N : Interactive Dynamic Visualization and Analysis Tool for Spiking Neural Networks
Author(s) :
Elbez, Hammouda [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Department of Computer Science [University of Mascara]
Kamel Benhaoua, Mohammed [Auteur]
Devienne, Philippe [Auteur]
Boulet, Pierre [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Department of Computer Science [University of Mascara]
Kamel Benhaoua, Mohammed [Auteur]
Devienne, Philippe [Auteur]

Boulet, Pierre [Auteur]

Conference title :
Content-Based Multimedia Indexing
City :
Lille
Country :
France
Start date of the conference :
2021-06-28
English keyword(s) :
Spiking neural networks
neuromorphic computing
visualization
analysis
big data
neuromorphic computing
visualization
analysis
big data
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
English abstract : [en]
Bio-inspired computing architectures enable ultralow power consumption and massive parallelism using neuromorphic computing, which is apt to implement Spiking Neural Networks (SNN). Such architectures are particularly ...
Show more >Bio-inspired computing architectures enable ultralow power consumption and massive parallelism using neuromorphic computing, which is apt to implement Spiking Neural Networks (SNN). Such architectures are particularly suitable for energy-constrained applications. A deeper understanding of Spiking Neural Networks (SNN) behavior during training is needed to improve these architectures. This paper presents VS2N, a web-based tool for interactive visualization and analysis of SNN activity over time. This simulator-independent tool offers a way to examine, analyze and validate different hypotheses about SNN activity. We present available analysis modules and use-cases of the tool as an example.Show less >
Show more >Bio-inspired computing architectures enable ultralow power consumption and massive parallelism using neuromorphic computing, which is apt to implement Spiking Neural Networks (SNN). Such architectures are particularly suitable for energy-constrained applications. A deeper understanding of Spiking Neural Networks (SNN) behavior during training is needed to improve these architectures. This paper presents VS2N, a web-based tool for interactive visualization and analysis of SNN activity over time. This simulator-independent tool offers a way to examine, analyze and validate different hypotheses about SNN activity. We present available analysis modules and use-cases of the tool as an example.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-03267042/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03267042/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03267042/file/VS2N%20%3A%20Interactive%20Dynamic%20Visualization%20and%20Analysis%20Tool%20for%20Spiking%20Neural%20Networks.pdf
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03267042/document
- Open access
- Access the document
- document
- Open access
- Access the document
- VS2N%20%3A%20Interactive%20Dynamic%20Visualization%20and%20Analysis%20Tool%20for%20Spiking%20Neural%20Networks.pdf
- Open access
- Access the document