Výsledky vyhledávání - "multi-tâche"

Regularized deep learning models for multi-anatomy segmentation in pediatric imaging

Autor: Boutillon, Arnaud

Publikováno v: Image Processing [eess.IV]. Ecole nationale supérieure Mines-Télécom Atlantique, 2022. English. ⟨NNT : 2022IMTA0311⟩

In medical imaging, segmentation using deep learning enables an automatic generation of anatomical models that are crucial for morphological evaluation. However, the scarcity of pediatric imaging resources may result in reduced accuracy and generaliz

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1398::36c62de4568a105b6e73462416683b82
https://theses.hal.science/tel-03906771

Zobrazit plný text záznamu

Modèles d’apprentissage profond régularisés pour la segmentation multi-anatomie en imagerie pédiatrique

Autor: Boutillon, Arnaud

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______166::36c62de4568a105b6e73462416683b82
https://theses.hal.science/tel-03906771

Zobrazit plný text záznamu

Traduction automatique neuronale multidomaine

Autor: Pham, Minh-Quang

Publikováno v: Artificial Intelligence [cs.AI]. Université Paris-Saclay, 2021. English. ⟨NNT : 2021UPASG109⟩

Today, neural machine translation (NMT) systems constitute state-of-the-art systems in machine translation. However, such translation models require relatively large train data and struggle to handle a specific domain text. A domain may consist of te

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______165::2750735ef72bb041cd3032bf1447f8cd
https://theses.hal.science/tel-03546910

Zobrazit plný text záznamu

Statistical Learning on Heterogeneous Medical Data with Bayesian Latent Variable Models: Application to Neuroimaging Dementia Studies

Autor: Antelmi, Luigi

Publikováno v: Statistics [math.ST]. INRIA Sophia Antipolis-Méditerranée; Université Côte d'Azur, 2021. English
Statistics [math.ST]. Université Côte d'Azur, 2021. English. ⟨NNT : 2021COAZ4050⟩

This thesis presents new computational tools for the joint modeling of multi-modal biomedical data,robust to missing data, with application to neuroimaging studies in dementia. The theoretical base for this work is the Variational Autoencoder (VAE),

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b11e7bf4604639e4569934c0cae40132
https://hal.archives-ouvertes.fr/tel-03289782/file/main.pdf

Zobrazit plný text záznamu

Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End

Autor: Heba, Abdelwahab

Publikováno v: Son [cs.SD]. Université toulouse 3 Paul Sabatier, 2021. Français

At Linagora, the OpenPaasNG project was launched in 2015 for a period of 4 years with the purpose of building a new generation of collaborative platform which provides a videoconferencing tool using artificial intelligence technologies such as speech

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::19af827229d3ecccbe97048feb6bf040
https://hal.archives-ouvertes.fr/tel-03269807/document

Zobrazit plný text záznamu

Intégration de tâches: étiquetage morpho-syntaxique, analyse syntaxique et analyse sémantique traités comme une tâche unique

Autor: Bernard, Timothée

Publikováno v: Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale
Traitement Automatique des Langues Naturelles
Traitement Automatique des Langues Naturelles, 2021, Lille, France. pp.268-269

International audience; Nous présentons des résumés en français et en anglais de l’article (Bernard, 2021), présenté lors de la conférence 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::703b53606d8659a6c58a1b56d27e6bda
https://hal.archives-ouvertes.fr/hal-03265885/file/227.pdf

Zobrazit plný text záznamu

Modèles statistiques pour méta-analyses d'études de neuroimagerie

Autor: Dockes, Jérôme

Publikováno v: Machine Learning [stat.ML]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLT048⟩

Thousands of neuroimaging studies are published every year. Exploiting this huge amount of results is difficult. Indeed, individual studies lack statistical power and report many spurious findings. Even genuine effects are often specific to particula

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2592::3fbab2623daf2159239eeb4ae76f262c
https://pastel.archives-ouvertes.fr/tel-02495783

Zobrazit plný text záznamu

Statistical models for comprehensive meta-analyses of neuroimaging studies

Autor: Dockes, Jérôme

Publikováno v: Machine Learning [stat.ML]. Télécom ParisTech, 2019. English
Machine Learning [stat.ML]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLT048⟩

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3fbab2623daf2159239eeb4ae76f262c
https://hal.archives-ouvertes.fr/tel-02469097/document

Zobrazit plný text záznamu

Designing Deep Architectures for Visual Understanding

Autor: Mordan, Taylor

Publikováno v: Computer Vision and Pattern Recognition [cs.CV]. Sorbonne Université, 2018. English. ⟨NNT : 2018SORUS270⟩
Computer Vision and Pattern Recognition [cs.CV]. EDITE, 2018. English

Nowadays, images are ubiquitous through the use of smartphones and social media. It then becomes necessary to have automatic means of processing them, in order to analyze and interpret the large amount of available data. In this thesis, we are intere

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::06bc3020d2f69cfe77e135fc8045d2b6
https://tel.archives-ouvertes.fr/tel-02868569/document

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání