Result Details

Hardware and Software Optimizations for Capsule Networks

MARCHISIO, A.; BUSSOLINO, B.; COLUCCI, A.; MRÁZEK, V.; HANIF, M.; MARTINA, M.; MASERA, G.; SHAFIQUE, M. Hardware and Software Optimizations for Capsule Networks. In Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing. Cham: Springer Nature Switzerland AG, 2023. p. 303-328. ISBN: 978-3-031-39932-9.
Type
chapter in a book
Language
English
Authors
MARCHISIO, A.
BUSSOLINO, B.
COLUCCI, A.
Mrázek Vojtěch, Ing., Ph.D., DCSY (FIT)
HANIF, M.
MARTINA, M.
MASERA, G.
Shafique Muhammad, FIT (FIT)
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. 

Keywords

capsule networks, hardware, software, neural architecture search

Published
2023
Pages
303–328
Book
Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing
ISBN
978-3-031-39932-9
Publisher
Springer Nature Switzerland AG
Place
Cham
DOI
10.1007/978-3-031-39932-9_12
EID Scopus
2-s2.0-85196470066
BibTeX 
@inbook{BUT193587,
  author="MARCHISIO, A. and BUSSOLINO, B. and COLUCCI, A. and MRÁZEK, V. and HANIF, M. and MARTINA, M. and MASERA, G. and SHAFIQUE, M.",
  title="Hardware and Software Optimizations for Capsule Networks",
  booktitle="Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing",
  year="2023",
  publisher="Springer Nature Switzerland AG",
  address="Cham",
  pages="303--328",
  doi="10.1007/978-3-031-39932-9\{_}12",
  isbn="978-3-031-39932-9"
}
Projects
Application-specific HW/SW architectures and their applications, BUT, Vnitřní projekty VUT, FIT-S-23-8141, start: 2023-03-01, end: 2026-02-28, running
Research groups
Evolvable Hardware Research Group (RG EHW)
Departments
Department of Computer Systems (DCSY)
Back to top