Probabilistic Foundations of Artificial Intelligence

How can we build systems that perform well in uncertain environments and unforeseen situations? How can we develop systems that exhibit ”intelligent” behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet. The course is designed for upper-level undergraduate and graduate students. VVZ Information is available here.
Syllabus
Date Topics Tutorial HW Solutions
Sep 18 Introduction, Propositional logic (Ch. 1 and 7.1-8.3) - - -
Sep 25 Propositional Resolution, First-order Logic (Ch. 7.1-8.3, Ch. 9.1-9.2, 9.5) [pdf] Hw1 [pdf] -
Oct 2 Inference in First Order Logic; Intro to probability (Ch. 9.1-9.2, 9.5, 13.1-5) [pdf] - Sol1 [pdf]
Oct 9 Bayesian Networks (Ch. 14.1-14.2) [pdf] Hw2 [pdf] -
Oct 16 Bayesian Networks: D-separation (Ch. 14.1-14.2) - - Sol2 [pdf]
Oct 23 Bayesian Networks: Exact Inference (Ch. 14.4) - Hw3 [pdf][zip] -
Oct 30 Belief Propagation (Ch. 14.5) - Hw4 [pdf][zip] Sol3 [pdf][zip]
Nov 6 Sampling, MCMC (Chapter 14.5; Bishop Chapter 8.4) - - Sol4 [pdf][zip]
Nov 13 Gibbs Sampling; Sequential models (Chapter 15.1-15.5) [pdf] Hw5 [pdf][zip] -
Nov 20 Dynamic Bayes nets, Particle filtering; MDPs (Chapter 17.1-17.3) - - Sol5 [pdf][zip] -
Nov 27 Probabilistic Planning: MDPs (Chapter 20.1-2), POMDPs - Hw6 [pdf] -
Dec 4 Learning Bayesian Networks (Chapter 20.1-2) [pdf] Hw7 [pdf][zip] Sol6 [pdf]
Dec 18 Reinforcement learning (Chapter 21.1-3) .Q-Learning demo (at Northwestern) [pdf] - Sol7 [pdf]
Jan 22 Exam review session [pdf] - -
Contact
Instructor Prof. Andreas Krause
Head TA Adish Singla
Assistants Yuxin Chen, Felix Berkenkamp, Jens Witkowski, Diego Ballesteros
Mailing List If you have any questions please send them to pai2015@lists.inf.ethz.ch from your ethz.ch address.
Lectures
Friday 10-12 CHN C 14
Tutorials
Friday 13-14 CHN C 14
Friday 14-15 CHN C 14
News
  • The materials from the exam review session have been posted.
  • Web site updated: If you can’t download some of the materials, please clear your browser cache.
  • The files are accessible from within ETH network. Please use VPN if you would like to access the files from outside.
  • First class on 18.9. First tutorial/recitation on 25.9.
Exam
The mode of examination is written, 120 minutes length. The language of examination is English. As written aids, you can bring one A4 sheet of paper (you can write on both sides), either handwritten or 11 point minimum font size. Please bring your Legi (ID card) for the exam. Please do not use cellphones / tablets in the exam. Calculators are not allowed.
You can find previous exams here: [2014], [2013], [2012].
Text Books
  • S. Russell, P. Norvig. Artificial Intelligence: A Modern Approach. 3rd edition
  • Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, 2007 (optional)