====== Intro au Learning ======


=== Quelques Bons Exposés sur le Deep Learning ===

  * [[https://www.college-de-france.fr/site/yann-lecun/_inaugural-lecture.htm | Leçon inaugurale de Yann Lecun au collège de France]]
  * [[https://www.youtube.com/watch?v=e2cAEBSXkT0 | les Math de l'intelligence, par Alain Tapp]]

=== Cours Universitaires ==

  * http://ai.berkeley.edu/lecture_slides.html
  * https://github.com/janishar/mit-deep-learning-book-pdf (MIT Book)
  * https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf (RL)

=== Intro à TensorFlow ===

  * http://playground.tensorflow.org/
  * https://www.youtube.com/watch?v=ru9dXF04iSE
  * https://github.com/Hvass-Labs/TensorFlow-Tutorials

=== Programmer avec TensorFlow & Keras===

  * Tutoriel Sympa sur Keras : 
    * https://machinelearningmastery.com/tutorial-first-neural-network-python-keras/
    * https://machinelearningmastery.com/how-to-choose-loss-functions-when-training-deep-learning-neural-networks/
    * https://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/
  * https://www.youtube.com/watch?v=O9yl9KKKoQI
  * Keras : https://www.tensorflow.org/guide/keras/overview (pip3 install keras)
  * Gym (game simulator) : https://gym.openai.com/ (pip3 install gym atari_py)
  * [[https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/quickstart/beginner.ipynb|quick start colab]]
  * Deep Q Learning (DQN) avec Keras+Gym : Cart Pole Sample 
    * https://keon.io/deep-q-learning/
    * https://medium.com/@gtnjuvin/my-journey-into-deep-q-learning-with-keras-and-gym-3e779cc12762

=== Atari 2600 ===

  * Playing Atari with Deep Reinforcement Learning, Deepmind.com (2013).
    * https://arxiv.org/pdf/1312.5602.pdf
  * Learning from the memory of Atari 2600 (2016).
    * https://deepsense.ai/playing-atari-on-ram-with-deep-q-learning/
    * https://github.com/sygi/deep_q_rl
    * https://cdn-sv1.deepsense.ai/wp-content/uploads/2016/09/1605.01335v1-4.pdf
  * DQN : Atari Breakout examples
    * https://becominghuman.ai/lets-build-an-atari-ai-part-1-dqn-df57e8ff3b26
    * https://github.com/rbrigden/breakout-ram-dqn
    * https://towardsdatascience.com/tutorial-double-deep-q-learning-with-dueling-network-architectures-4c1b3fb7f756
    * https://github.com/andi611/DQN-Deep-Q-Network-Atari-Breakout-Tensorflow
    * https://deepsense.ai/playing-atari-on-ram-with-deep-q-learning/
    * ...
  * Reinforcement Learning + Keras + Atari : https://github.com/rlcode/reinforcement-learning
  * DDQN + Genetic
    * https://towardsdatascience.com/atari-reinforcement-learning-in-depth-part-1-ddqn-ceaa762a546f
    * https://towardsdatascience.com/atari-solving-games-with-ai-part-2-neuroevolution-aac2ebb6c72b

=== About Graph ===

  * Graph Representation Learning: https://www.youtube.com/watch?v=YrhBZUtgG4E
  * GCN : https://towardsdatascience.com/how-to-do-deep-learning-on-graphs-with-graph-convolutional-networks-7d2250723780
  * https://rlgm.github.io/papers/41.pdf
  * Semi-Supervised Classification with Graph Convolutional Networks: https://arxiv.org/abs/1609.02907

=== Fun! ===

  * https://github.com/greerviau/SnakeAI + https://www.youtube.com/watch?v=zIkBYwdkuTk
  * Alpha Toe
    * https://github.com/DanielSlater/AlphaToe
    * https://www.youtube.com/watch?v=Meb5hApAnj4
  * [[https://www.youtube.com/channel/UCVso5UVvQeGAuwbksmA95iA|Chaîne Youtube de T. Neveu]]