November 2024
Intermediate to advanced
252 pages
7h 2m
French
Content preview from Apprentissage profond à partir de zéroBecome an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Index
Symboles
A
- gradients accumulés, Coding Up Gradient Accumulation, Accumulation des gradients pour les poids dans un RNN
- Fonctions d'activation, Connexion au cerveau, Note sur les fonctions d'activation - Unjuste milieu : Tanh
- autoencoders, Une approche pour les situations sans aucune étiquette-Implémentation d'un autoencodeur dans PyTorch.
- Différenciation automatique (autodiff), Différenciation automatique - Expliquerce qui s'est passé
- mise en commun des moyennes, couches de mise en commun
B
- rétropropagation, La réponse, La rétropagation
- passe en arrière
- code décrivant, Code-Descriptionvisuelle deces gradients
- diagramme représentant, Diagramme
- description mathématique, Math-Theanswer
- multiplication matricielle par lots, Convolutions par multiplication matricielle-Convolutionspar multiplication matricielle
- Formation par lots, Mise en œuvre de la formation par lots
- terme de biais, Les éléments constitutifs des réseaux neuronaux : Couches, blocs de construction sur blocs de construction, Gradient de la perte par rapport aux termes de biais
- laramification, la principale limitation : Gérer les ramifications- La limitation clé : Gérer les ramifications
C
- règle de la chaîne
- rétropropagation et, La réponse
- code décrivant, Code-Code
- défini, La règle de la chaîne
- diagramme représentant, Diagramme
- chaînes plus longues, un exemple decode un peu plus ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.