CSE 250A. Principles of Artificial Intelligence:
Probabilistic Reasoning and Decision-Making
| Administrivia | Syllabus | Piazza | GradeSource |
Subject
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.
Prerequisites
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.
Relation to other courses
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.
Administrivia
- Instructor: Lawrence Saul
- Teaching assistants (TAs):
Shivani Agrawal (sha014
eng.ucsd.edu)
Purvi Desai (pdesaieng.ucsd.edu)
Suqi Liu (suqics.ucsd.edu)
Wenjia Ouyang (weouyangeng.ucsd.edu)
Feichao Qian (feqianeng.ucsd.edu)
- Lectures: Tue/Thu 11:00 am - 12:20 pm, Center 119
- Instructor office hour: Fri 10:05-11 am, CSE 3214
- TA discussion sections:
Fri 11-noon, WLH 2113 (Shivani)
Fri 3-4 pm, WLH 2207 (Suqi)
Fri 4-5 pm, WLH 2207 (Purvi)
Mon 2-3 pm, WLH 2207 (Feichao)
Mon 5-6 pm, WLH 2207 (Wenjia)
- TA office hours (in CSE basement):
Mon 5-6 pm (Feichao)
Wed 8-9 am (Wenjia)
Wed 9-10 am (Purvi)
Thu 5-6 pm (Shivani)
Fri 5-6 pm (Suqi)
- Grading: homework (50%), two quizzes (50%).
Textbooks
The course does not closely follow a particular text; the lectures are meant to be self-contained. Nevertheless, the following texts (though not required) may be useful as general references:- Artificial Intelligence: A Modern Approach (Russell & Norvig, 2010)
- Machine Learning: A Probabilistic Perspective (Murphy, 2012)
- Reinforcement Learning: An Introduction (Sutton & Barto, 1998)
- Pattern Recognition and Machine Learning (Bishop, 2006)
Syllabus
| Tue Mar 29 | Administrivia and course overview. | |
| Thu Mar 31 | Modeling uncertainty, review of probability, explaining away. | |
| Tue Apr 05 | Belief networks: from probabilities to graphs. | HW 1 out. |
| Thu Apr 07 | Conditional independence, d-separation, polytrees. | |
| Tue Apr 12 | Algorithms for exact and approximate inference. | HW 1 due. HW 2 out. |
| Thu Apr 14 | Maximum likelihood estimation; Markov models of language; naive Bayes models of text. | |
| Tue Apr 19 | Linear and logistic regression. Numerical optimization. | HW 2 due. HW 3 out. |
| Thu Apr 21 | Latent variable modeling. Expectation-Maximization (EM) algorithm. Auxiliary functions. | |
| Tue Apr 26 | EM algorithm: derivation, proof of convergence. | HW 3 due. |
| Thu Apr 28 | Examples of EM; applications to language modeling. | |
| Tue May 03 | Quiz #1 | HW 4 out. |
| Thu May 05 | Hidden Markov models, automatic speech recognition, Viterbi algorithm. | |
| Tue May 10 | Forward-backward algorithm, Gaussian mixture models, Kalman filters. | HW 4 due. HW 5 out. |
| Thu May 12 | Reinforcement learning (RL), Markov decision processes. | |
| Tue May 17 | Policy evaluation, policy improvement. | HW 5 due. HW 6 out. |
| Thu May 19 | Policy iteration, value iteration. | |
| Tue May 24 | Stochastic approximation theory, temporal difference prediction. | HW 6 due. HW 7 out. |
| Thu May 26 | Q-learning, extensions of RL. | |
| Tue May 31 | Review or bonus topic (if time) | |
| Thu Jun 02 | Quiz #2 | |
| Tue Jun 07 | no class | HW 7 due |