CSE 250A. Principles of Artificial Intelligence:

Administrivia  Syllabus  Piazza  GradeSource 
Probabilistic methods for reasoning and decisionmaking 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 highlevel 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 22  Administrivia and course overview.  
Tue Sep 27  Modeling uncertainty, review of probability, explaining away.  HW 1 out. 
Thu Sep 29  Belief networks: from probabilities to graphs.  
Tue Oct 04  Conditional independence, dseparation, polytrees.  HW 1 due. HW 2 out. 
Thu Oct 06  Algorithms for exact and approximate inference.  
Tue Oct 11  Maximum likelihood estimation; Markov models of language; naive Bayes models of text.  HW 2 due. HW 3 out. 
Thu Oct 13  Linear and logistic regression. Numerical optimization.  
Tue Oct 18  Latent variable modeling. ExpectationMaximization (EM) algorithm. Auxiliary functions.  HW 3 due. HW 4 out. 
Thu Oct 20  EM algorithm: derivation, proof of convergence.  
Tue Oct 25  Examples of EM; applications to language modeling.  HW 4 due. HW 5 out. 
Thu Oct 27  Hidden Markov models, automatic speech recognition, Viterbi algorithm.  
Tue Nov 01  Forwardbackward algorithm, Gaussian mixture models, Kalman filters.  HW 5 due. HW 6 out. 
Thu Nov 03  Reinforcement learning (RL), Markov decision processes.  
Tue Nov 08  Policy evaluation, policy improvement.  HW 6 due. HW 7 out. 
Thu Nov 10  Policy iteration, value iteration.  
Tue Nov 15  Stochastic approximation theory, temporal difference prediction.  HW 7 due. HW 8 out. 
Thu Nov 17  Qlearning, extensions of RL.  
Tue Nov 22  Bonus topic (if time).  HW 8 due. 
Thu Nov 24  Thanksgiving Holiday  
Tue Nov 29  Final exam: part one (inclass)  
Thu Dec 01  Final exam: part two (inclass)  