Zobrazeno 1 - 10
of 490
pro vyhledávání: '"Preda, Marius"'
Autor:
Hubens, Nathan, Delvigne, Victor, Mancas, Matei, Gosselin, Bernard, Preda, Marius, Zaharia, Titus
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained environment such
Externí odkaz:
http://arxiv.org/abs/2303.10999
Neural network pruning is a widely used strategy for reducing model storage and computing requirements. It allows to lower the complexity of the network by introducing sparsity in the weights. Because taking advantage of sparse matrices is still chal
Externí odkaz:
http://arxiv.org/abs/2203.05807
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for real-time ap
Externí odkaz:
http://arxiv.org/abs/2112.08227
Introducing sparsity in a neural network has been an efficient way to reduce its complexity while keeping its performance almost intact. Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to convergence, 2) prun
Externí odkaz:
http://arxiv.org/abs/2107.02086
Publikováno v:
Energy and Buildings, Elsevier, 2021
In this paper, we propose a new end-to-end methodology to optimize the energy performance as well as comfort and air quality in large buildings without any renovation work. We introduce a metamodel based on recurrent neural networks and trained to pr
Externí odkaz:
http://arxiv.org/abs/2105.02814
In this paper, we propose a new end-to-end methodology to optimize the energy performance and the comfort, air quality and hygiene of large buildings. A metamodel based on a Transformer network is introduced and trained using a dataset sampled with a
Externí odkaz:
http://arxiv.org/abs/2006.12390
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:
INFOSFERA - Revista de studii de securitate si Informații pentru Apărare / INFOSFERA - Journal of Security Studies and Defense. XII(3):58-63
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=1007263
Publikováno v:
INFOSFERA - Revista de studii de securitate si Informații pentru Apărare / INFOSFERA - Journal of Security Studies and Defense. XII(2):59-67
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=988364
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.