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 150 covers largely the same material as CSE 250A, but at a slower pace and less advanced mathematical level. The homework assignments (and exams) in CSE 250A are longer and more challenging.
Thu Oct 02  Administrivia and course overview.  
Tue Oct 07  Modeling uncertainty, review of probability, explaining away.  HW 1 out. 
Thu Oct 09  Belief networks: from probabilities to graphs.  
Tue Oct 14  Conditional independence, dseparation, polytrees.  HW 1 due. HW 2 out. 
Thu Oct 16  Algorithms for exact and approximate inference.  
Tue Oct 21  Maximum likelihood estimation; Markov models of language; naive Bayes models of text.  HW 2 due. HW 3 out. 
Thu Oct 23  Linear and logistic regression. Numerical optimization.  
Tue Oct 28  Latent variable modeling. ExpectationMaximization (EM) algorithm. Auxiliary functions.  HW 3 due. 
Thu Oct 30  EM algorithm: derivation, proof of convergence.  
Tue Nov 04  Quiz #1  HW 4 out. 
Thu Nov 06  Examples of EM; applications to language modeling.  
Tue Nov 11  Veteran's Day  HW 5 out. 
Thu Nov 13  Hidden Markov models, automatic speech recognition, Viterbi algorithm.  HW 4 due. 
Tue Nov 18  Forwardbackward algorithm, Gaussian mixture models, Kalman filters.  HW 5 due. HW 6 out. 
Thu Nov 20  Reinforcement learning (RL), Markov decision processes.  
Tue Nov 25  Policy evaluation, policy improvement.  HW 6 due. 
Thu Nov 27  Thanksgiving Holiday  
Tue Dec 02  Quiz #2  HW 7 out. 
Thu Dec 04  Policy iteration, value iteration.  
Tue Dec 09  Stochastic approximation theory, temporal difference prediction.  
Thu Dec 11  Qlearning, extensions of RL.  HW 7 due. 
Fri Dec 19  Final exam. 