« Apprentissage dirigé » : différence entre les versions
Aucun résumé des modifications Balise : Éditeur de wikicode 2017 |
Aucun résumé des modifications |
||
Ligne 10 : | Ligne 10 : | ||
== Anglais == | == Anglais == | ||
'''teacher forcing''' | '''teacher forcing''' | ||
Teacher forcing is a method for quickly and efficiently training recurrent neural network models that use the ground truth from a prior time step as input. | |||
It is a network training method critical to the development of deep learning language models used in machine translation, text summarization, and image captioning, among many other applications. | |||
<small> | <small> | ||
[https://www.apprentissageprofond.org/ Source : ''L'apprentissage profond'', Ian Goodfellow, Yoshua Bengio et Aaron Courville Éd. Massot 2018 ] | [https://www.apprentissageprofond.org/ Source : ''L'apprentissage profond'', Ian Goodfellow, Yoshua Bengio et Aaron Courville Éd. Massot 2018 ] | ||
[https://machinelearningmastery.com/teacher-forcing-for-recurrent-neural-networks/ Source : machinelearningmastery.com ] |
Version du 31 décembre 2020 à 07:40
en construction
Définition
Français
apprentissage dirigé
Anglais
teacher forcing
Teacher forcing is a method for quickly and efficiently training recurrent neural network models that use the ground truth from a prior time step as input.
It is a network training method critical to the development of deep learning language models used in machine translation, text summarization, and image captioning, among many other applications.
Source : L'apprentissage profond, Ian Goodfellow, Yoshua Bengio et Aaron Courville Éd. Massot 2018
Contributeurs: Imane Meziani, Jean Benoît Morel, Jacques Barolet, Patrick Drouin, wiki