General Information

Course Outline

The course covers advanced topics in machine learning. Including:

  • Introduction Graphical models - Bayesian networks and Markov networks
  • Exact and approximate inference in graphical models
  • Parameter estimation in graphical models
  • Structured prediction
  • Unsupervised deep learning
  • Bandits
  • Reinforcement Learning
  • Advanced generalization bounds (stability, Rademacher complexity)

Formalities

Staff

li.ca.uat.tsop|rimag#nosrebolG rimA .forP (homepage)

Feel free to coordinate reception hours with me via email.

Grade

There will be up to five exercises, involving theoretical and applied aspects of the material. Programming will be in Python and also using the TensorFlow library. Submission of all exercises is mandatory for passing the course.

You will also submit a research project. The project could either theory or application oriented, as long as it's sufficiently challenging and related to the material taught in the course.

We will allow group submissions for exercises and projects. The bound on group sizes will be decided on soon.

Final Grade is made out of:

  • 80% Project
  • 20% Exercises
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License