Deep neural networks under stress
In recent years, deep architectures have been used for transfer learning with state-of-the-art
performance in many datasets. The properties of their features remain, however, largely …
performance in many datasets. The properties of their features remain, however, largely …
An rss pathloss considered distance metric learning for fingerprinting indoor localization
Y Zhang, L Ma, Y Xu, Y Sun - 2019 IEEE Global …, 2019 - ieeexplore.ieee.org
The immense diffusion of smart mobile devices increase the usage of WiFi as a state-of-the-
art wireless communication standard dramatically, and it also renders fingerprinting method …
art wireless communication standard dramatically, and it also renders fingerprinting method …
Triangular similarity metric learning: A siamese architecture approach
L Zheng - 2016 - hal.science
In many machine learning and pattern recognition tasks, there is always a need for
appropriate metric functions to measure pairwise distance or similarity between data, where …
appropriate metric functions to measure pairwise distance or similarity between data, where …
Towards Autonomous PErceptual Systems
S Herbin - 2020 - hal.science
The objective of this document is to introduce the principle of Autonomous PErceptual
System (APES) as an object of study. The functionalities of artificial perception, in particular …
System (APES) as an object of study. The functionalities of artificial perception, in particular …
Deep representation spaces
M Carvalho - 2018 - theses.hal.science
In recent years, Deep Learning techniques have swept the state-of-the-art of many
applications of Machine Learning, becoming the new standard approach for them. The …
applications of Machine Learning, becoming the new standard approach for them. The …
Trajectory Privacy Preservation and Lightweight Blockchain Techniques for Mobility-Centric IoT
AB Shahid - 2019 - search.proquest.com
Various research efforts have been undertaken to solve the problem of trajectory privacy
preservation in the Internet of Things (IoT) of resource-constrained mobile devices. Most …
preservation in the Internet of Things (IoT) of resource-constrained mobile devices. Most …
[PDF][PDF] Triangular Similarity Metric Learning: a Siamese Architecture Approach
BP DORIZZI, N THOME, K IDRISSI - 2016 - hal.science
" No two leaves are exactly alike."—Gottfried Wilhelm Leibniz This dictum of Leibniz reveals
that differences are ubiquitous in this world. Besides, we can also realize another fact that he …
that differences are ubiquitous in this world. Besides, we can also realize another fact that he …
Apprentissage et exploitation de représentations sémantiques pour la classification et la recherche d'images
M Bucher - 2018 - hal.science
Dans cette thèse nous étudions différentes questions relatives à la mise en pratique de
modèles d'apprentissage profond. En effet malgré les avancées prometteuses de ces …
modèles d'apprentissage profond. En effet malgré les avancées prometteuses de ces …