In recent years different types of Residual Neural Networks (ResNets, for short) have been introduced to improve the performance of deep Convolutional Neural Networks. To cope with the possible redundancy of the layer structure of ResNets and to use them on devices with limited computational capabilities, several tools for exploring and compressing such networks have been proposed. In this paper, we provide a contribution in this setting. In particular, we propose an approach for the representation and compression of a ResNet based on the use of a multilayer network. This is a structure sufficiently powerful to represent and manipulate a ResNet, as well as other families of deep neural networks. Our compression approach uses a multilayer network to represent a ResNet and to identify the possible redundant convolutional layers belonging to it. Once such layers are identified, it prunes them and some related ones obtaining a new compressed ResNet. Experimental results demonstrate the suitability and effectiveness of the proposed approach.

Representation and Compression of Residual Neural Networks through a Multilayer Network Based Approach / Amelio, A.; Bonifazi, G.; Cauteruccio, F.; Corradini, E.; Marchetti, M.; Ursino, D.; Virgili, L.. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 215:(2023). [10.1016/j.eswa.2022.119391]

Representation and Compression of Residual Neural Networks through a Multilayer Network Based Approach

G. Bonifazi;F. Cauteruccio;E. Corradini;M. Marchetti;D. Ursino;L. Virgili
2023-01-01

Abstract

In recent years different types of Residual Neural Networks (ResNets, for short) have been introduced to improve the performance of deep Convolutional Neural Networks. To cope with the possible redundancy of the layer structure of ResNets and to use them on devices with limited computational capabilities, several tools for exploring and compressing such networks have been proposed. In this paper, we provide a contribution in this setting. In particular, we propose an approach for the representation and compression of a ResNet based on the use of a multilayer network. This is a structure sufficiently powerful to represent and manipulate a ResNet, as well as other families of deep neural networks. Our compression approach uses a multilayer network to represent a ResNet and to identify the possible redundant convolutional layers belonging to it. Once such layers are identified, it prunes them and some related ones obtaining a new compressed ResNet. Experimental results demonstrate the suitability and effectiveness of the proposed approach.
2023
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0957417422024095-main.pdf

Solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso: Tutti i diritti riservati
Dimensione 5.42 MB
Formato Adobe PDF
5.42 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
ResNetExplanation.pdf

embargo fino al 01/12/2024

Tipologia: Documento in post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza d'uso: Creative commons
Dimensione 6.37 MB
Formato Adobe PDF
6.37 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/308781
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 19
social impact