CSE 250A. Principles of Artificial Intelligence:
Probabilistic methods for reasoning and decision-making under uncertainty. Topics include: inference and learning in directed probabilistic graphical models; prediction and planning in Markov decision processes; applications to computer vision, robotics, speech recognition, natural language processing, and information retrieval.
The course is aimed broadly at advanced undergraduates and beginning graduate students in mathematics, science, and engineering. Prerequisites are elementary probability, multivariable calculus, linear algebra, and basic programming ability in some high-level language such as C, Java, or Matlab. Programming assignments are completed in the language of the student's choice.
CSE 250a covers largely the same topics as CSE 150 (as I teach it), but at a faster pace and more advanced mathematical level. The homework assignments and exams in CSE 250A are also longer and more challenging. In general you should not take CSE 250a if you already have taken CSE 150 from me in a previous quarter.
|Thu Sep 27||Administrivia and course overview.|
|Tue Oct 02||Modeling uncertainty, review of probability, explaining away.||HW 1 out.|
|Thu Oct 04||Belief networks: from probabilities to graphs.|
|Tue Oct 9||Conditional independence, d-separation, polytrees.||HW 1 due.
HW 2 out.
|Thu Oct 11||Algorithms for exact and approximate inference.|
|Tue Oct 16||Maximum likelihood estimation; Markov models of language; naive Bayes models of text.||HW 2 due.
HW 3 out.
|Thu Oct 18||Linear and logistic regression. Numerical optimization.|
|Tue Oct 23||Latent variable modeling. Expectation-Maximization (EM) algorithm. Auxiliary functions.||HW 3 due.
HW 4 out.
|Thu Oct 27||EM algorithm: derivation, proof of convergence.|
|Tue Oct 30||Examples of EM; applications to language modeling.||HW 4 due.
HW 5 out.
|Thu Nov 01||Hidden Markov models, Viterbi algorithm.|
|Tue Nov 06||Midterm, 8-10 pm, Center 115/119 [A/B]|
|Thu Nov 08||Forward-backward algorithm, Gaussian mixture models, Kalman filters.||HW 5 due.
HW 6 out.
|Tue Nov 13||Reinforcement learning (RL), Markov decision processes.||HW 6 due.
HW 7 out.
|Thu Nov 15||Policy evaluation, policy improvement.|
|Tue Nov 20||Policy iteration, value iteration.||HW 7 due.
HW 8 out.
|Thu Nov 22||Thanksgiving Holiday|
|Tue Nov 27||Stochastic approximation theory, temporal difference prediction.||HW 8 due.
HW 9 out.
|Thu Nov 29||Q-learning, extensions of RL.|
|Tue Dec 04||Bonus topics or catch-up.|
|Thu Dec 06||Bonus topics or review.||HW 9 due|
|Mon Dec 10||Final exam, 7-10 pm, rooms TBA.|