A comprehensive survey on hardware-aware neural architecture search
Neural Architecture Search (NAS) methods have been growing in popularity. These
techniques have been fundamental to automate and speed up the time consuming and error …
techniques have been fundamental to automate and speed up the time consuming and error …
Representing deep neural networks latent space geometries with graphs
Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art
performance in many machine learning tasks. The core principle of DL methods consists of …
performance in many machine learning tasks. The core principle of DL methods consists of …
Convolutional neural networks pruning and its application to embedded vision systems
H Tessier - 2023 - theses.hal.science
Being at the state of the art in many domains, such as computer vision, convolutional neural
networks became a staple for many industrial applications, such as autonomous vehicles …
networks became a staple for many industrial applications, such as autonomous vehicles …
Graphs as Tools to Improve Deep Learning Methods
C Lassance, M Bontonou, M Hamidouche… - arXiv preprint arXiv …, 2021 - arxiv.org
In recent years, deep neural networks (DNNs) have known an important rise in popularity.
However, although they are state-of-the-art in many machine learning challenges, they still …
However, although they are state-of-the-art in many machine learning challenges, they still …
Efficient Hardware-aware Neural Architecture Search for Edge Computing
H Benmeziane - 2023 - theses.hal.science
It is widely anticipated that inference models based on Deep Neural Networks (DNN) will be
actively employed in many edge platforms due to several compelling reasons. Firstly, DNNs …
actively employed in many edge platforms due to several compelling reasons. Firstly, DNNs …
Représentation uniforme de l'imagerie médicale
L Fezai - 2023 - theses.hal.science
Le domaine médical est un vaste domaine d'application de l'intelligence artificielle. Malgré
les avancées récentes, il y reste une large marge d'innovation et d'amélioration face à des …
les avancées récentes, il y reste une large marge d'innovation et d'amélioration face à des …
DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems
Learning deep representations to solve complex machine learning tasks has become the
prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden …
prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden …
Élagage de réseaux profond de neurones par dégradation sélective des pondérations
Les réseaux de neurones profonds sont le standard incontournable de l'apprentissage
automatique. Cependant, pour atteindre les meilleures performances, ils requièrent des …
automatique. Cependant, pour atteindre les meilleures performances, ils requièrent des …
Graphs for deep learning representations
C Lassance - arXiv preprint arXiv:2012.07439, 2020 - arxiv.org
In recent years, Deep Learning methods have achieved state of the art performance in a vast
range of machine learning tasks, including image classification and multilingual automatic …
range of machine learning tasks, including image classification and multilingual automatic …
[引用][C] Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay.
H Tessier, PSA Groupe, V Gripon, M Léonardon… - arXiv preprint arXiv …, 2020