532c - Advanced Machine Learning

This course tackles some of the fundamental problems at the interface of learning, decision theory and probability. The course develops the theoretical foundations, representations and algorithms for active learning, value of information problems, experimental design, attention, optimal control and reinforcement learning. The course will present these developments in the the context of web crawling, relevance feedback in HCI, robotic exploration, question answering systems, clinical trials, active vision, active labelling of database entries, network problems, graphics and animation, control, surveillance and more.

When: T-Th 2:00-3:30pm

Where: Dempster 201

Instructor: Nando de Freitas (nando at cs)

Nando's Office hours: Mon (10:30am-12), Tue (11am-12) (cicsr 183).

Recommended books:

  • Artificial Intelligence: A Modern Aproach
    by Stuart Russell and Peter Norvig.
  • Markov Decision Processes
    by Martin Puterman.
  • Neuro-Dynamic Programming
    by Dimitri Bertsekas and John Tsitsiklis.
  • Reinforcement Learning: An Introduction
    by Richard Sutton and Andrew Barto.
  • Dynamic Programming and Optimal Control
    by Dimitri Bertsekas.
  • Statistical Decision Theory and Bayesian Analysis
    by James Berger.

    Recommended websites:

  • Andrew Ng
  • Richard Sutton
  • Satinder Singh
  • Ben van Roy
  • Carlos Guestrin
  • Joelle Pineau
  • Pascal Poupart
  • Michael Littman

    Grading

  • Assignments: 20
  • Midterm : 30
  • Project: 30
  • Project presentation: 20

    Assignments

  • Assignments will involve both written and matlab programming problems.
  • All assignments are due on the specified time. 20% off for each day late. Assignments will not be accepted after 5 days late.

    Newsgroup: ubc.courses.cpsc.550
  •