Administration:

Course teachers: Prof Gal Chechik, Zacharie Cohen

Prerequisits Home assignments in the course are given in python.

Course Requirements: To get a passing grade in this course, students must submit all the home assignments. The final project is due by Feb 1st 2021.

Final grade: The final grade is based on 30% home assignments, and 70% final project.

List of classes and topics

  1. Introduction to machine learning. Motivation, generalization
  2. The perceptron algorithm
  3. Gradient Descent, Supervised learning
  4. Logistic regression
  5. Non linear classifiers, multi-layer perceptrons
  6. Generalization and over fitting in deep neural networks
  7. Convolutional Neural networks
  8. Unsupervised learning, PCA
  9. Unsupervised learning, Autoencoders
  10. Self-supervised learning
  11. Graph-convolution networks
  12. RNNs and LSTMS
  13. Summary: Brain networks vs deep networks