Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Qararyah, Fareed"'
Depthwise and pointwise convolutions have fewer parameters and perform fewer operations than standard convolutions. As a result, they have become increasingly used in various compact DNNs, including convolutional neural networks (CNNs) and vision tra
Externí odkaz:
http://arxiv.org/abs/2404.19331
Autor:
Mika, Kevin, Griessl, René, Kucza, Nils, Porrmann, Florian, Kaiser, Martin, Tigges, Lennart, Hagemeyer, Jens, Trancoso, Pedro, Azhar, Muhammad Waqar, Qararyah, Fareed, Zouzoula, Stavroula, Ménétrey, Jämes, Pasin, Marcelo, Felber, Pascal, Marcus, Carina, Brunnegard, Oliver, Eriksson, Olof, Salomonsson, Hans, Ödman, Daniel, Ask, Andreas, Casimiro, Antonio, Bessani, Alysson, Carvalho, Tiago, Gugala, Karol, Zierhoffer, Piotr, Latosinski, Grzegorz, Tassemeier, Marco, Porrmann, Mario, Heyn, Hans-Martin, Knauss, Eric, Mao, Yufei, Meierhöfer, Franz
Publikováno v:
CF'23: 20th ACM International Conference on Computing Frontiers, May 2023, Bologna, Italy
The VEDLIoT project aims to develop energy-efficient Deep Learning methodologies for distributed Artificial Intelligence of Things (AIoT) applications. During our project, we propose a holistic approach that focuses on optimizing algorithms while add
Externí odkaz:
http://arxiv.org/abs/2305.05388
Many state-of-the-art Deep Neural Networks (DNNs) have substantial memory requirements. Limited device memory becomes a bottleneck when training those models. We propose ParDNN, an automatic, generic, and non-intrusive partitioning strategy for DNNs
Externí odkaz:
http://arxiv.org/abs/2008.08636
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Parallel Computing July 2021 104-105
