몬트리올 대학의 MILA 랩이 주관하는 2017 DL & RL 서머 스쿨 강의 동영상이 VideoLectures를 통해 공개되었습니다. 이번 서머 스쿨의 강의는 총 36개로 이 중에 2개는 공개되지 못하고 딥러닝 25개와 강화학습 9개가 공개되었습니다. 강의자들의 이름만 봐도 후덜덜하네요. : )

• Deep Learning Summer School
  1. Machine Learning(1:26:30), Doina Precup
  2. Neural Networks(3:03:15), Hugo Larochelle
  3. Recurrent Neural Networks (RNNs)(1:25:47), Yoshua Bengio
  4. Probabilistic numerics for deep learning(1:30:25), Michael Osborne
  5. Generative Models I(1:18:03), Ian Goodfellow
  6. Theano(34:51), Pascal Lamblin
  7. AI Impact on Jobs(1:05:58), Michael Osborne
  8. Introduction to CNNs(1:28:54), Richard Zemel
  9. Structured Models/Advanced Vision(1:28:22), Raquel Urtasun
  10. Torch/PyTorch(55:15), Soumith Chintala
  11. Generative Models II(1:28:25), Aaron Courville
  12. Natural Language Understanding(1:24:30), Phil Blunsom
  13. Natural Language Processing(1:23:42), Phil Blunsom
  14. Bayesian Hyper Networks(15:25), David Scott Krueger
  15. Gibs Net(14:01), Alex Lamb
  16. Pixel GAN autoencoder(12:23), Alireza Makhzani
  17. CRNN’s(16:16), Rémi Leblond, Jean-Baptiste Alayrac
  18. Deep learning in the brain(1:23:34), Blake Aaron Richards
  19. Theoretical Neuroscience and Deep Learning Theory(1:32:38), Surya Ganguli
  20. Marrying Graphical Models & Deep Learning(1:23:14), Max Welling
  21. Learning to Learn(1:21:05), Nando de Freitas
  22. Automatic Differentiation(1:18:12), Matthew James Johnson
  23. Combining Graphical Models and Deep Learning(1:30:25), Matthew James Johnson
  24. Domain Randomization for Cuboid Pose Estimation(12:52), Jonathan Tremblay
  25. tbd(15:48), Rogers F. Silva
  26. What Would Shannon Do? Bayesian Compression for DL(16:26), Karen Ullrich
  27. On the Expressive Efficiency of Overlapping Architectures of Deep Learning(13:13), Or Sharir
• Reinforcement Learning Summer School
  1. Reinforcement Learning(1:29:32), Joelle Pineau
  2. Policy Search for RL(1:28:26), Pieter Abbeel
  3. TD Learning(1:26:24), Richard S. Sutton
  4. Deep Reinforcement Learning(1:21:20), Hado van Hasselt
  5. Deep Control(1:23:52), Nando de Freitas
  6. Theory of RL(1:23:58), Csaba Szepesvári
  7. Reinforcement Learning(1:29:02), Satinder Singh
  8. Safe RL(1:21:44), Philip S. Thomas
  9. Applications of bandits and recommendation systems(43:54), Nicolas Le Roux