Zobrazeno 1 - 10 of 49 pro vyhledávání: '"apprentissage incrémental"'
1
Système tutoriel intelligent pour l'apprentissage par croquis Projet Sketch
Autor: Barchouch, Islam, Anquetil, Eric, Girard, Nathalie, Krichen, Omar
Publikováno v: SIFED 2023 – Symposium International Francophone sur l’Ecrit et le Document
SIFED 2023 – Symposium International Francophone sur l’Ecrit et le Document, Jun 2023, Paris, France
International audience
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4d8c546ccff3eabe6eae09ed66fec571
https://inria.hal.science/hal-04129595/document
Zobrazit plný text záznamu
2
Incremental learning in data : Application to personalized emotion recognition
Autor: Gonzalez, Jordan
Publikováno v: Traitement du signal et de l'image [eess.SP]. HESAM Université, 2022. Français. ⟨NNT : 2022HESAE052⟩
The field of affective computing, which has been growing rapidly over the last few decades, aims to create new interactive systems that are able to perceive the emotional state of their human interlocutors and adapt to them automatically.It is quite
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_____10147::10be839d06bc93ad4e4a23449e42291c
https://pastel.hal.science/tel-04060780
Zobrazit plný text záznamu
3
Pseudo-Labeling for Class Incremental Learning
Autor: Lechat, Alexis, Herbin, Stéphane, Jurie, Frédéric
Publikováno v: BMVC 2021 : The British Machine Vision Conference
BMVC 2021 : The British Machine Vision Conference, Nov 2021, virtuel, United Kingdom
International audience; Class Incremental Learning (CIL) consists in training a model iteratively with limited amount of data from few classes that will never be seen again, resulting in catastrophic forgetting and lack of diversity. In this paper, w
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::69e2ed25cb54e1d832a981b4dcb14499
https://hal.archives-ouvertes.fr/hal-03464466
Zobrazit plný text záznamu
4
Towards protean learning : accomodating signature changes in artificial agents
Autor: Iago Bonnici
Publikováno v: Intelligence artificielle [cs.AI]. Université Montpellier, 2021. Français. ⟨NNT : 2021MONTS034⟩
HAL
In the domain of Machine Learning (ML), computer scientists develop sophisticated learning agents: programs aimed to automatically discover procedures to solve difficult automation tasks like artificial vision, robot control, etc. Some tasks are chal
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3b0fcefb41842682885aae2a8250a0ee
https://tel.archives-ouvertes.fr/tel-03414933/file/BONNICI_2021_archivage.pdf
Zobrazit plný text záznamu
5
Vers un apprentissage protéiforme : accommoder les changements de signature des agents artificiels
Autor: Bonnici, Iago
Publikováno v: Artificial Intelligence [cs.AI]. Universite de Montpellier 2, 2021. English
Agents in Machine Learning are computer procedures aimed to automatically discover solutions to complex automation tasks like artificial vision, robot control, etc. This searching process called "learning" is characterized, like any computer procedur
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8130767ff774f338e4bfc885dd1d7a04
https://hal.archives-ouvertes.fr/tel-03432860
Zobrazit plný text záznamu
6
From Satellite Images to Vector Maps
Autor: Tasar, Onur
Publikováno v: Computer Vision and Pattern Recognition [cs.CV]. Inria Sophia Antipolis-Méditerranée; Université Côte d'Azur, 2020. English
With the help of significant technological developments over the years, it has been possible to collect massive amounts of remote sensing data. For example, the constellations of various satellites are able to capture large amounts of remote sensing
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______212::6d76bb7a6235001d008e86e2bd0d0561
https://hal.archives-ouvertes.fr/tel-02989681
Zobrazit plný text záznamu
7
Des images satellites aux cartes vectorielles
Autor: Tasar, Onur
Publikováno v: Image Processing [eess.IV]. Université Côte d'Azur, 2020. English. ⟨NNT : 2020COAZ4063⟩
Computer Vision and Pattern Recognition [cs.CV]. Inria Sophia Antipolis-Méditerranée; Université Côte d'Azur, 2020. English
With the help of significant technological developments over the years, it has been possible to collect massive amounts of remote sensing data. For example, the constellations of various satellites are able to capture large amounts of remote sensing
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::80857f0b6c21dd1b004742611ab9d360
https://theses.hal.science/tel-02989681v2
Zobrazit plný text záznamu
8
Continual learning for image classification
Autor: Dutt, Anuvabh
Publikováno v: Artificial Intelligence [cs.AI]. Université Grenoble Alpes, 2019. English. ⟨NNT : 2019GREAM063⟩
This thesis deals with deep learning applied to image classification tasks. The primary motivation for the work is to make current deep learning techniques more efficient and to deal with changes in the data distribution. We work in the broad framewo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______212::8ef75289af08c0aa32604e2f47b35409
https://tel.archives-ouvertes.fr/tel-02907322
Zobrazit plný text záznamu
9
Apprentissage continu pour la classification des images
Autor: Dutt, Anuvabh
Publikováno v: Artificial Intelligence [cs.AI]. Université Grenoble Alpes, 2019. English. ⟨NNT : 2019GREAM063⟩
This thesis deals with deep learning applied to image classification tasks. The primary motivation for the work is to make current deep learning techniques more efficient and to deal with changes in the data distribution. We work in the broad framewo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2592::8ef75289af08c0aa32604e2f47b35409
https://tel.archives-ouvertes.fr/tel-02907322
Zobrazit plný text záznamu
10
Continual forgetting-free deep learning from high-dimensional data streams
Autor: Besedin, Andrey
Publikováno v: Neural and Evolutionary Computing [cs.NE]. Conservatoire national des arts et metiers-CNAM, 2019. English. ⟨NNT : 2019CNAM1263⟩
In this thesis, we propose a new deep-learning-based approach for online classification on streams of high-dimensional data. In recent years, Neural Networks (NN) have become the primary building block of state-of-the-art methods in various machine l
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::86c5731cb31e74f063adaedaec7bdb37
https://tel.archives-ouvertes.fr/tel-02484715
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje