Archivio Istituzionale della RicercaAmong advanced Deep Neural Network models, Capsule Networks (CapsNets) have shown high learning and generalization capabilities for advanced tasks. Their capability to learn hierarchical information of features makes them appealing in many applications. However, their compute-intensive nature poses several challenges for their deployment on resource-constrained devices. This chapter provides an optimization flow at the software and at the hardware level for improving the energy efficiency of the CapsNets execution.
Hardware and Software Optimizations for Capsule Networks / Marchisio, Alberto; Bussolino, Beatrice; Colucci, Alessio; Mrazek, Vojtech; Hanif, Muhammad Abdullah; Martina, Maurizio; Masera, Guido; Shafique, Muhammad - In: Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing / Pasricha S., Shafique M.. - ELETTRONICO. - [s.l] : Springer, 2024. - ISBN 9783031399312. - pp. 303-328 [10.1007/978-3-031-39932-9_12]
Hardware and Software Optimizations for Capsule Networks
Martina, Maurizio;Masera, Guido;
2024
Abstract
Among advanced Deep Neural Network models, Capsule Networks (CapsNets) have shown high learning and generalization capabilities for advanced tasks. Their capability to learn hierarchical information of features makes them appealing in many applications. However, their compute-intensive nature poses several challenges for their deployment on resource-constrained devices. This chapter provides an optimization flow at the software and at the hardware level for improving the energy efficiency of the CapsNets execution.
| File | Dimensione | Formato | |
|---|---|---|---|
|
bussolino_springer_2023.pdf
accesso riservato
Descrizione: Chapter editorial version
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.35 MB
Formato
Adobe PDF
|
1.35 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
EmbeddedMLBook_CapsNets_chapter.pdf
Open Access dal 11/10/2024
Descrizione: Versione autori
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
2.29 MB
Formato
Adobe PDF
|
2.29 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2990298