Machine Learning Gems

Here is my list of great machine learning resources.

Lastly updated on 2017-03-06

Courses

  • “Machine Learning” with Andew NG, provided by Coursera / Stanford U – CS229. It is like Machine Learning 101. It helps you get the basics right – regressions, learnable params, classification, neural nets, validation, how to construct models, etc. [videos] [slides]
  • “Convolutional Neural Networks for Visual Recognition” with Andrej Karpathy, Justin Johnson, and Fei-Fei Li, provided by Stanford U – CS231n [videos] [slides]
  • “Deep Learning” with Yann LeCun, provided by College De France [videos] [slides]
  • “Probabilistic Graphical Models” with Daphne Koller, provided by Coursera / Stanford U – CS228 [videos] [slides]
  • “Neural Networks for Machine Learning” with Geoffrey Hinton, provided by Coursera / University of Toronto [videos] [slides]
  • “Representation Learning and Deep Learning” with Yoshua Bengio, provided by University of Montreal – IFT6266 H-2016 [videos] [slides]
  • “Machine Learning” with Nando De Freitas, provided by Oxford U [videos] [slides]
  • “Neural networks” with Hugo Larochele, provided by Universit? de Sherbrooke [videos] [slides]
  • “Tutorial on Deep Learning” with Ruslan Salakhutdinov, provided by Simons Institute, Berkeley U [videos] [slides]
  • “Deep Learning for Natural Language Processing” with
    Richard Socher, provided by Stanford University [web] [videos] [slides]
  • “Tensorflow for Deep Learning” provided by Stanford University [web], [slides], [video]

Tutorials

  • NIPS 2016, Long Beach [web]
  • ICML 2016, New York City [web]
  • ICLR 2016, San Juan [web]

Books

  • “Deep Learning” by Ian Goodfellow and Yoshua Bengio and Aaron Courville [pdf] [paper]
  • “Pattern Recognition and Machine Learning” by Christopher Bishop [paper]

Blogs

Tools

  • torchpytorch
  • tensorflow, keras
  • caffe

External lists

  • “Most cited papers since 2012” by Terry Taewoong Um [web]
  • “Deep Learning for NLP resources” by Andrew Thomas [web]