Understanding deep architectures and the effect of unsupervised pre-training
Cette thèse porte sur une classe d'algorithmes d'apprentissage appelés architectures profondes. Il existe des résultats qui indiquent que les représentations peu profondes et locales ne sont pas suffisantes pour la modélisation des fonctions comportant plusieurs facteurs de variation. Nous...
Main Author: | Erhan, Dumitru |
---|---|
Other Authors: | Bengio, Yoshua |
Language: | en |
Published: |
2011
|
Subjects: | |
Online Access: | http://hdl.handle.net/1866/5022 |
Similar Items
-
Understanding deep architectures and the effect of unsupervised pre-training
by: Erhan, Dumitru
Published: (2011) -
Identifying electrons with deep learning methods
by: Kahya, Emre Onur
Published: (2021) -
Learning to sample from noise with deep generative models
by: Bordes, Florian
Published: (2017) -
Real-Time Reinforcement Learning
by: Ramstedt, Simon
Published: (2020) -
Structured prediction and generative modeling using neural networks
by: Kastner, Kyle
Published: (2017)