Compression of Deep Neural Networks for Space Autonomous Systems

[en] Efficient compression techniques are required to deploy deep neural networks (DNNs) on edge devices for space resource utilization tasks. Two approaches are investigated.

Centre de recherche :

Interdisciplinary Centre for Security, Reliability and Trust (SnT) > CVI² - Computer Vision Imaging & Machine Intelligence

Disciplines :

Aérospatiale, astronomie & astrophysique
Sciences informatiques
Ingénierie, informatique & technologie: Multidisciplinaire, généralités & autres

Auteur, co-auteur :

SHNEIDER, Carl ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

SINHA, Nilotpal ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

JAMROZIK, Michele Lynn ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

ASTRID, Marcella ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

ROSTAMI ABENDANSARI, Peyman ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

KACEM, Anis ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

SHABAYEK, Abd El Rahman ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

AOUADA, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2

Co-auteurs externes :

Langue du document :

Anglais

Titre :

Compression of Deep Neural Networks for Space Autonomous Systems

Date de publication/diffusion :

19 avril 2023

Nombre de pages :

Nom de la manifestation :

Luxembourg Space Resources Week 2023

Lieu de la manifestation :

Luxembourg, Luxembourg

Date de la manifestation :

19-04-2023 to 21-04-2023

Manifestation à portée :

International

Focus Area :

Security, Reliability and Trust
Computational Sciences

URL complémentaire :

https://zenodo.org/record/7931156

Projet FnR :

FNR15965298 - Enabling Learning And Inferring Compact Deep Neural Network Topologies On Edge Devices, 2021 (01/09/2022-31/08/2025) - Djamila Aouada

Intitulé du projet de recherche :

Enabling Learning And Inferring Compact Deep Neural Network Topologies On Edge Devices (ELITE)

Organisme subsidiant :

FNR - Fonds National de la Recherche

Disponible sur ORBilu :

depuis le 02 octobre 2023

Statistiques

Nombre de vues

168 (dont 6 Unilu)

Nombre de téléchargements

101 (dont 16 Unilu)

Voir plus de statistiques