.. blogpost::
    :title: Cours de deep learning appliqués au NLP
    :keywords: deep learning, NLP
    :date: 2017-11-13
    :categories: cours
    :lid: blog-stanford-nlp-deep

    `Stanford University School of Engineering <https://www.youtube.com/channel/UCdKG2JnvPu6mY1NDXYFfN0g>`_
    met en ligne beaucoup de cours dont les suivants
    `Natural Language Processing with Deep Learning <https://www.youtube.com/watch?v=OQQ-W_63UgQ&list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6>`_.
    C'est l'état de l'art cette année.

    * `Lecture 1: Natural Language Processing with Deep Learning <https://www.youtube.com/watch?v=OQQ-W_63UgQ>`_
    * `Lecture 2: Word Vector Representations: word2vec <https://www.youtube.com/watch?v=ERibwqs9p38>`_
    * `Lecture 3: GloVe: Global Vectors for Word Representation <https://www.youtube.com/watch?v=ASn7ExxLZws&feature=youtu.be&t=57m10s>`_
    * `Lecture 4: Word Window Classification and Neural Networks <https://www.youtube.com/watch?v=uc2_iwVqrRI>`_
    * `Lecture 5: Backpropagation and Project Advice <https://www.youtube.com/watch?v=isPiE-DBagM>`_
    * `Lecture 6: Dependency Parsing <https://www.youtube.com/watch?v=PVShkZgXznc>`_
    * `Lecture 7: Introduction to TensorFlow <https://www.youtube.com/watch?v=PicxU81owCs>`_
    * `Lecture 8: Recurrent Neural Networks and Language Models <https://www.youtube.com/watch?v=Keqep_PKrY8>`_
    * `Lecture 9: Machine Translation and Advanced Recurrent LSTMs and GRUs <https://www.youtube.com/watch?v=QuELiw8tbx8>`_
    * `Lecture 10: Neural Machine Translation and Models with Attention <https://www.youtube.com/watch?v=IxQtK2SjWWM>`_
    * `Lecture 11: Gated Recurrent Units and Further Topics in NMT <https://www.youtube.com/watch?v=6_MO12fPC-0>`_
    * `Lecture 12: End-to-End Models for Speech Processing <https://www.youtube.com/watch?v=3MjIkWxXigM>`_
    * `Lecture 13: Convolutional Neural Networks <https://www.youtube.com/watch?v=Lg6MZw_OOLI>`_
    * `Lecture 14: Tree Recursive Neural Networks and Constituency Parsing <https://www.youtube.com/watch?v=RfwgqPkWZ1w>`_
    * `Lecture 15: Coreference Resolution <https://www.youtube.com/watch?v=rpwEWLaueRk>`_
    * `Lecture 16: Dynamic Neural Networks for Question Answering <https://www.youtube.com/watch?v=T3octNTE7Is>`_
    * `Lecture 17: Issues in NLP and Possible Architectures for NLP <https://www.youtube.com/watch?v=B4v545V3Dq0>`_
    * `Lecture 18: Tackling the Limits of Deep Learning for NLP <https://www.youtube.com/watch?v=JYwNmSe4HqE>`_

    Une série d'articles sur le deep learning :

    * `Applied Deep Learning - Part 1: Artificial Neural Networks <https://towardsdatascience.com/applied-deep-learning-part-1-artificial-neural-networks-d7834f67a4f6>`_
    * `Applied Deep Learning - Part 2: Real World Case Studies <https://towardsdatascience.com/applied-deep-learning-part-2-real-world-case-studies-1bb4b142a585>`_
    * `Applied Deep Learning - Part 3: Autoencoders <https://towardsdatascience.com/applied-deep-learning-part-3-autoencoders-1c083af4d798>`_
    * `Applied Deep Learning - Part 4: Convolutional Neural Networks <https://towardsdatascience.com/applied-deep-learning-part-4-convolutional-neural-networks-584bc134c1e2>`_

    A propos des *Generative Adversarial Networks* :

    * `Overview of GANs (Generative Adversarial Networks) - Part I <https://towardsdatascience.com/overview-of-gans-generative-adversarial-networks-part-i-ac78ec775e31>`_
    * `Generative Adversarial Networks — Part II <https://towardsdatascience.com/generative-adversarial-networks-part-ii-6212f7755c1f>`_

    Un résultat d'expérience qui est amené à prendre plus d'importance.
    Une couche d'un réseau de neurones profond est consistitué de plusieurs ensembles
    de neurones non connecté (des filtres). Ces filtres reçoivent tous les mêmes
    entrées. L'article proposent une façon de spécialiser chaque filtre plus rapidement
    en routant (en pondérant) les exemples entre chauqe couche.

    * `What is a CapsNet or Capsule Network? <https://hackernoon.com/what-is-a-capsnet-or-capsule-network-2bfbe48769cc>`_
    * `Dynamic Routing Between Capsules <https://arxiv.org/abs/1710.09829v2>`_
    * `capsLayer.py <https://gist.github.com/debarko/7c87c10921f0ed0c4f7641b4e14f2071>`_

    Enfin :

    * `Deep learning architecture diagrams <http://fastml.com/deep-learning-architecture-diagrams/>`_
    * `10 Advanced Deep Learning Architectures Data Scientists Should Know! <https://www.analyticsvidhya.com/blog/2017/08/10-advanced-deep-learning-architectures-data-scientists/>`_