Načítá se...

AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution

This article proposes a novel network model to achieve better accurate residual binarized convolutional neural networks (CNNs), denoted as AresB-Net. Even though residual CNNs enhance the classification accuracy of binarized neural networks with increasing feature resolution, the degraded classifica...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:PeerJ Comput Sci
Hlavní autor: Kim, HyunJin
Médium: Artigo
Jazyk:Inglês
Vydáno: PeerJ Inc. 2021
Témata:
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC8022573/
https://ncbi.nlm.nih.gov/pubmed/33834112
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.7717/peerj-cs.454
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!