Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Apprentissage de Métrique"'
Autor:
Compagnon, Paul
Publikováno v:
Artificial Intelligence [cs.AI]. Université de Lyon, 2021. English. ⟨NNT : 2021LYSEI033⟩
This thesis has been realized thanks to a cifre between Orange labs Grenoble and the LIRIS at Lyon. This thesis aims at proposing new neural network approaches to retrieve the habitual behaviors of fragile people in order to provide them with a monit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d4e184242eafb6d21c8d00b5e4f20f44
https://tel.archives-ouvertes.fr/tel-03407186/document
https://tel.archives-ouvertes.fr/tel-03407186/document
Autor:
Cattan, Grégoire, Quemy, Alexandre
Signal analysis of brain-computer interface (BCI) based on electroencephalography (EEG) is complex and, therefore constitutes a practical impediment for application developers and content providers. In this study, we evaluate the use of the hypergrap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::52a52585783059ea40a099b6a630efad
https://hal.archives-ouvertes.fr/hal-03359078v1
https://hal.archives-ouvertes.fr/hal-03359078v1
Autor:
Kerdoncuff, Tanguy
The Optimal Transport theory not only defines a notion of distance between probability measures, but can also align two distributions. During the past few years, Optimal Transport found many applications in Machine Learning, such as the approximation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______166::ef87d7058da70fb939cb3502ef7aea5d
https://theses.hal.science/tel-03722856
https://theses.hal.science/tel-03722856
Autor:
Nagorny, Pierre
Publikováno v:
Systèmes et contrôle [cs.SY]. Université Savoie Mont Blanc, 2020. Français. ⟨NNT : 2020CHAMA008⟩
Inline quality control of the product is an important objective for industries growth. Controlling a product quality requires measurements of its quality characteristics. One hundred percent control is an important objective to overcome the limits of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::87ff861a6689038aa7e7e3cfc469fff8
https://theses.hal.science/tel-03181778
https://theses.hal.science/tel-03181778
Autor:
Pan, Jiajun
Publikováno v:
Artificial Intelligence [cs.AI]. Université de Nantes, 2019. English
Metric learning is a branch of machine learning, and more specifically representation learning, which involves learning the parameters of a metric in order to improve its intrinsic qualities when using it. In this thesis, we summarize recent developm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fa089f1d89021ddb4ea79bcb3c49ccfb
https://hal.archives-ouvertes.fr/tel-03180284/document
https://hal.archives-ouvertes.fr/tel-03180284/document
Publikováno v:
Conférence Nationale en Intelligence Artificielle (CNIA)
Conférence Nationale en Intelligence Artificielle (CNIA), Jul 2019, Toulouse, France
Conférence Nationale en Intelligence Artificielle (CNIA), Jul 2019, Toulouse, France
National audience; Nous traitons le problème de la comparaison des objets3D déformables représentés par des graphes tels que lestessellations triangulaires. Nous proposons une nouvelletechnique d’appariement de graphes pour mesurer la distancee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b1e559607c321e83ed560fb043dfad00
https://hal.archives-ouvertes.fr/hal-02180118
https://hal.archives-ouvertes.fr/hal-02180118
Autor:
Carvalho, Micael
Publikováno v:
Artificial Intelligence [cs.AI]. Sorbonne Université, 2018. English. ⟨NNT : 2018SORUS292⟩
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 architectures issued from these techniques have been used for transfer learning, whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2592::bdfe66905b5837c65ac3d5ff3bef1611
https://tel.archives-ouvertes.fr/tel-02503198/file/CARVALHO_Micael_these_2018.PDF
https://tel.archives-ouvertes.fr/tel-02503198/file/CARVALHO_Micael_these_2018.PDF
Autor:
Carvalho, Micael
Publikováno v:
Artificial Intelligence [cs.AI]. Sorbonne Université, 2018. English. ⟨NNT : 2018SORUS292⟩
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 architectures issued from these techniques have been used for transfer learning, whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::bdfe66905b5837c65ac3d5ff3bef1611
https://tel.archives-ouvertes.fr/tel-02503198/file/CARVALHO_Micael_these_2018.PDF
https://tel.archives-ouvertes.fr/tel-02503198/file/CARVALHO_Micael_these_2018.PDF
Autor:
El Moussawi, Adnan
Les travaux de cette thèse s’intéressent à l’exploration de la multiplicité des solutions de clustering. Le but est de proposer aux experts marketing un outil interactif d’exploration des données clients qui considère les préférences de
Externí odkaz:
http://www.theses.fr/2018TOUR4010/document
Autor:
Schmitt, Thomas
Notre recherche porte sur la recommandation de nouvelles offres d'emploi venant d'être postées et n'ayant pas d'historique d'interactions (démarrage à froid). Nous adaptons les systèmes de recommandations bien connus dans le domaine du commerce
Externí odkaz:
http://www.theses.fr/2018SACLS210/document