딥 러닝 (Deep learning)

• 강의실: 공학 3관 xxx호
• Textbooks
  • I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT Press, 2016 [book]
• References
  • Tutorial for Theano [link]
  • Deep learning tutorial using Theano [link]
  • TensorFlow [link]
  • TensorFlow Tutorial [link]
  • Torch [link]
• Reference textbooks
  • Kevin Patrick Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012 [link]
  • Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2007 [link]
  • Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998 [link] [2nd_edition]
  • S. O. Haykin, Neural Networks and Learning Machines (3rd Edition), Pearson, 2008 [link]
  • Andrew Gelman, John B. Carlin, Hal S. Stern, David B. Dunson, Aki Vehtari, Donald B. Rubin, Bayesian Data Analysis, Chapman and Hall/CRC, 2013 link]
  • Y. Bengio, Learning Deep Architectures for AI, 2009 [pdf]
  • Hinton's Lecture on Advanced Machine Learning [link]
• Others
  • Artificial Intelligence and Life in 2030 [pdf]
  • Y LeCun, Y Bengio, G Hinton, Deep learning, Nature, 2015[pdf(slide)][pdf]
  • IEEE Neural Network Piorneer Award Recipients [link]
  • Michael Jordan on deep learning [link]
  • Bay Area Deep Learning School at Stanford [link]
  • Towards an integration of deep learning and neuroscience, 2016 [pdf]
  • Hybrid computing using a neural network with dynamic external memory, 2016 [link] [s1_pdf]

• Lecture 1: Introduction [pdf]
• Lecture 2: Machine Learning Basics [pdf]
  • Linear algebra [pdf]
  • Machine Learning (CS 229) [link]
  • Supervised Learning [link][pdf]
  • VC Dimension [pdf]
• Lecture 2(additional): Introduction to Theano [pdf]
• Lecture 3: Feedforward Neural Networks [pdf]
  • Who Invented Backpropagation? [link]
• Lecture 3(additional): Backpropagation on Computational Graphs [pdf]
• Lecture 4: Regularization for Deep learning [pdf]
• Lecture 5: Convolutional Networks [pdf]
• Directions in Convolutional Neural Networks at Google [link]
• Deep residual learning [link]
• Lecture 6: Recurrent and Recursive Nets [pdf]
• Lecture 7: Autoencoders [pdf]
• Lecture 8: Graphical models [pdf]
• Lecture 9: Monte Carlo Methods [pdf]
• Lecture on Chap11 - Bayesian Data Analysis: Posterior simultation [[link]
• Metropolis-Hastings [pdf], Gibbs sampling [pdf], Markov chains [pdf], Markov chain Monte Carlo [pdf]
• Lecture 10: Confronting the Partition Function [pdf]
• Lecture 11: Deep Belief Network [pdf]
• An introduction to Restricted Boltzmann Machines [pdf]
• Lecture 12: Approximate Inference [pdf]
• Lecture on probabilistic graphical models at CMU [link]
• Expectation-Maximization in PGM [pdf]
• Variational inference in PGM [pdf]
• Lecture 13: Deep Generative Models [pdf]
• Deep Boltzmann Machines [pdf]
• Generative Adversarial Netweorks [pdf]
• Lecture 14: Differentiable Neural Computer (DNC) [pdf]
• Neural Turing Machine [pdf]
• Memory Network [pdf]
• Lecture 15: Deep Reinforcement Learning [pdf]