Deep Learning en détail#
Notebooks
(à venir foolbox)
Cours
Artificial Intelligence, Revealed (1) : article de blog et vidéos expliquant les différents concepts du deep learning
colah’s blog (2016/08) blog/cours sur le deep learning
Course notes for CS224N Winter17 (Stanford)
Tutoriels
Image Similarity Ranking using Microsoft Cognitive Toolkit (CNTK)
Tutoriels avec CNTK : ces notebooks sont bien illlustrés (GAN - Generative Models).
Tutoriels avec TensorFlow : ce ne sont pas les seuls mais ils ont l’avantage d’être bien illustrés (Adversarial Training).
Machine Learning is Fun! Part 3: Deep Learning and Convolutional Neural Networks
Machine Learning is Fun! Part 4: Modern Face Recognition with Deep Learning
Deep Learning - The Straight Dope : séries de notebooks de difficulté graduelle
Sites
Liens
Articles scientifiques
LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
Deep Learning, Yoshua Bengio, Ian Goodfellow and Aaron Courville
Wide & Deep Learning: Better Together with TensorFlow, Wide & Deep Learning for Recommender Systems
Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey
Deep Learning (wikipédia)
Evaluation of Deep Learning Toolkits (2015/12)
Understanding Deep Learning Requires Rethinking Generalization
On the importance of initialization and momentum in deep learning
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models
Chiffres, Textes
One weird trick for parallelizing convolutional neural networks
ImageNet Classification with Deep Convolutional Neural Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Multi-Digit Recognition Using A Space Displacement Neural Network
Neural Network Architectures, Convolutional Neural Networks (CNNs / ConvNets)
Benchmarks
Plus théoriques
Lectures deep text
Efficient Estimation of Word Representations in Vector Space, Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean,
Distributed Representations of Words and Phrases and their Compositionality, Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, Jeff Dean,
word2vec Parameter Learning Explained, Xin Rong,
Tutorial on Auto-Encoders, Piotr Mirowski
Pretrained Character Embeddings for Deep Learning and Automatic Text Generation
Vus dans des conférences
Fast R-CNN (dotAI)
Mask R-CNN (dotAI)
Modèle Tenserflow (modèle adaptés pour du transfer learning : ResNet, Inception) (dotAI)
Deep learning embarqué
Modules - deep learning
pytorch : design plus simple que tous les autres
climin (algorithme de back propagation)
tensorflow (Google)
Modules - à suivre
Federated Learning: Collaborative Machine Learning without Centralized Training Data
foolbox : trouver des petites perturbations des données qui trompent les réseaux de neurones