Lecture 1: Fundamentals of Machine Learning

Main References

• “Machine Learning: A Probabilistic Perspective”, K. Murphy

• “Understanding Machine Learning: From Theory to Algorithms”, Shai Ben-David and Shai Shalev-Shwartz

• “Generative Adversarial Networks”(MS Thesis), Y. (see chapter 2)

Further References

• “Introduction to statistical learning theory”, O. Bousquet, S. Boucheron, G. Lugosi

• “The Lack of A Priori Distinctions Between Learning Algorithms”, D. Wolpert

• “254A, Notes 0: A review of probability theory”, Terence Tao

Lecture 2: Neural Networks - Fundamentals

Main References

• “Deep Learning”, LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. (see chapter 5 and 6)

Lecture 3: Neural Networks - Designing Neural Networks

• Check the classes of Nando de Freitas on modular formulation of NNs lec8 - lec9.
• Further references for working with PyTorch:
  • https://github.com/jcjohnson/pytorch-examples by Justin Johnson.
  • https://pytorch.org/tutorials/
  • Lectures from Fleuret François EE-559 Deep Learning course:
    • Tensor Basics and Linear Regression
    • High dimension tensors
    • Tensor internals
    • Autograd
    • PyTorch modules
    • Writing a PyTorch module

Lecture 9: Introduction to Tensorflow

• https://www.tensorflow.org/tutorials/
• CS 20SI: Tensorflow for Deep Learning Research
• Tutorials by Magnus Erik Hvass Pedersen -
• Another good set of examples
• More links
• More examples with Lucid