Representation and compression of Residual Neural Networks through a multilayer network based approach

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 capabil...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Expert systems with applications Ročník 215; s. 119391
Hlavní autoři: Amelio, Alessia, Bonifazi, Gianluca, Cauteruccio, Francesco, Corradini, Enrico, Marchetti, Michele, Ursino, Domenico, Virgili, Luca
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.04.2023
Témata:
Complex networks
Compression algorithm
Convolutional layer pruning
Convolutional Neural Networks
Multilayer networks
Residual Neural Networks
Convolutional layer pruning
Residual Neural Networks
Convolutional Neural Networks
Compression algorithm
Multilayer networks
Complex networks
ISSN:0957-4174, 1873-6793
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 of a ResNet model through a multilayer network.•An approach to compress a ResNet through its multilayer network representation.•A compression approach tested on ResNet20,ResNet56,ResNet110 and CIFAR10, CIFAR100.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2022.119391