Bibliographie Algolittéraire

Voici les textes qui nous ont accompagnés lors des sessions de travail sur le traitement du langage naturel dans l'apprentissage automatique.

Réseau neuronal et language

• CS224n: Natural Language Processing with Deep Learning (Stanford course) - http://web.stanford.edu/class/cs224n/syllabus.html
• GloVe: Global Vectors for Word Representation - https://nlp.stanford.edu/projects/glove/
• The Unreasonable Effectiveness of Recurrent Neural Networks - http://karpathy.github.io/2015/05/21/rnn-effectiveness/

Biais en language

• Caliskan, A., Bryson, J. J. and Narayanan, A., 2017. Semantics derived automatically from language corpora contain human-like biases. Science, 356 (6334), pp. 183-186.
• Bolukbasi, T., Chang, K. W., Zou, J. and Saligrama, V., 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. CoRR.
• Rob Speer, How to make a racist AI without really trying - https://gist.github.com/rspeer/ef750e7e407e04894cb3b78a82d66aed#file-how-to-make-a-racist-ai-without-really-trying-ipynb

Réseau neuronal et Aprrentissage profond

• Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning - http://www.deeplearningbook.org/
• Michael Nielsen, Neural Networks and Deep Learning - http://neuralnetworksanddeeplearning.com

• Neural Networks, Manifolds, and Topology - http://colah.github.io/posts/2014-03-NN-Manifolds-Topology/
• Visualizing Representations: Deep Learning and Human Beings - http://colah.github.io/posts/2015-01-Visualizing-Representations/

Contexte général

• Halpern, O., 2014. Beautiful Data: A History of Vision and Reason since 1945, Duke Press - https://www.dukeupress.edu/beautiful-data, http://www.orithalpern.net/
• Hayles, Katherine N., 2016. Unthought. The Power of Cognitive Nonconscious
• McKenzie, Adrian, 2015. The production of prediction: What does machine learning want? http://journals.sagepub.com/doi/abs/10.1177/1367549415577384?journalCode=ecsa
• Speech and Language Processing, Daniel Jurafsky and James H. Martin, Stanford University, 2017: https://web.stanford.edu/~jurafsky/slp3/ed3book.pdf

Logiciels pour l'apprentissage profond et réseau nueronal

• Tensorflow (Google): https://www.tensorflow.org/

Quelques introductions:

• Sam Abrahams, Danijar Hafner, Erik Erwitt, Ariel Scarpinelli, TensorFlow for Machine Intelligence. A Hands-On Introduction to Learning Algorithms. Bleeding Edge Press (2016)
• Rodolfo Bonnin, Building Machine Learning Projects with TensorFlow. Packt Publishing (2016)
• Nick McClure, TensorFlow Machine Learning Cookbook. Packt Publishing (2017) (more in-depth but also a slightly steeper learning curve)
• Scikit Learn: http://scikit-learn.org

Outils de simulation

• Simulation en navigateur: http://playground.tensorflow.org
• Introduction qui utilise TensorFlow: https://cloud.google.com/blog/big-data/2016/07/understanding-neural-networks-with-tensorflow-playground