.. image:: pystat.png
:height: 20
:alt: Statistique
:target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-data-scientist
Deep Learning en détail
+++++++++++++++++++++++
*Notebooks*
.. toctree::
:maxdepth: 2
../notebooks/_gs2a_deep
(à venir foolbox)
*Cours*
* `Deep Learning course: lecture slides and lab notebooks `_
* `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
* `Tutoriels avec CNTK `_
* `Course notes for CS224N Winter17 `_ (Stanford)
*Tutoriels*
* `Building Autoencoders in Keras `_
* `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 `_
* `Object detection using Fast R-CNN `_
* `Deep Learning - The Straight Dope `_ :
séries de notebooks de difficulté graduelle
*Sites*
* `Tinker With a Neural Network Right Here in Your Browser `_
* `ConvNetJS `_
* `Databricks / Deep Learning `_
*Liens*
* `Four deep learning trends from ACL 2017 (1) `_
* `Four deep learning trends from ACL 2017 (2) `_
*Articles scientifiques*
* `LightRNN: Memory and Computation-Efficient Recurrent Neural Networks `_
* `Deep learning architecture diagrams `_
* `Factorized Convolutional Neural Networks `_
* `Deep Residual Learning for Image Recognition `_
* `Deep Learning `_, Yoshua Bengio, Ian Goodfellow and Aaron Courville
* `LeNet5 `_
* `mxnet `_
* `Benchmarking State-of-the-Art Deep Learning Software Tools `_
* `Wide & Deep Learning: Better Together with TensorFlow `_,
`Wide & Deep Learning for Recommender Systems `_
* `To go deep or wide in learning? `_
* `Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey `_
* `Tutorial: Learning Deep Architectures `_
* `Deep Learning `_ (wikipédia)
* `Fast R-CNN `_ (voir `Object Detection using Fast R CNN `_)
* `Evaluation of Deep Learning Toolkits `_ *(2015/12)*
* `Understanding Deep Learning Requires Rethinking Generalization `_
* `Training Deep Nets with Sublinear Memory Cost `_
* `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 `_
* `Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documents `_
* `Neural Network Architectures `_,
`Convolutional Neural Networks (CNNs / ConvNets) `_
* `Transfer Learning `_
*Benchmarks*
* `Benchmarking CNTK on Keras: is it Better at Deep Learning than TensorFlow? `_
(`code `_)
*Plus théoriques*
* `Why Does Unsupervized Deep Learning Work? - A perspective from group theory `_
* `Deep Learning of Representations: Looking Forward `_
* `Why Does Unsupervised Pre-training Help Deep Learning? `_
*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)*
* `Domain-Adversarial Training of Neural Networks `_ *(dotAI)*
*Deep learning embarqué*
* `TensorFlow sur Android `_
* `TensorFlow sur RasberryPI `_
*Modules - deep learning*
* `pytorch `_ : design plus simple que tous les autres
* `keras `_
* `mxnet `_
* `caffe `_ (`installation `_)
* `climin `_ (algorithme de back propagation)
* `tensorflow `_ (Google)
* `cntk `_
*Modules - à suivre*
* `chainer `_
* `Federated Learning: Collaborative Machine Learning without Centralized Training Data `_
* `foolbox `_ :
trouver des petites perturbations des données qui trompent les réseaux de neurones