| CSE 150 - Winter 2014 Introduction to Artificial Intelligence: Probabilistic Reasoning and Decision Making
Prof. Lawrence Saul |
 |
 |
 |
 |
| Administrivia | Syllabus | Piazza | GradeSource | CAPEs |
Subject
This course will introduce students to the probabilistic and statistical models at the heart of modern artificial intelligence. Specific topics to be covered include: probabilistic methods for reasoning and decision-making under uncertainty; inference and learning in Bayesian networks; prediction and planning in Markov decision processes; applications to intelligent systems, speech and natural language processing, information retrieval, and robotics.
Prerequisites
This course is aimed very broadly at undergraduates in mathematics, science, and engineering. Prerequisites are elementary probability, linear algebra, and calculus, as well as basic programming ability in some high-level language such as C, Java, Matlab, R, or Python. (Programming assignments are completed in the language of the student's choice.) Students of all backgrounds are welcome.
Texts
The course will not closely follow a particular text. The following texts, though not required, may be useful as general references:- K. Korb and A. Nicholson, Bayesian Artificial Intelligence.
- S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach.
- R. Sutton and A. Barto, Reinforcement Learning: An Introduction.
Instructors
- Lecturer: Lawrence Saul (saul
cs.ucsd.edu)
- Teaching assistants:
Yuncong Chen (yuc007eng.ucsd.edu)
Vineel Konduru (vkonduruucsd.edu)
Soham Shah (srshaheng.ucsd.edu)
Kritika Singh (kritikaeng.ucsd.edu)
Meetings
- Lectures: Tue/Thu 5:00-6:20 pm, WLH-2005.
- Office hour: Fri 9-10 am, EBU3B-3214.
- Discussion sections:
- Mon 4:00 WLH 2207 (Kritika)
- Mon 6:00 CSB 004 (Vineel)
- Fri 11:00 PCYNH 121 (Yuncong)
- Fri 4:00 WLH 2207 (Soham)
- Mon 4:00 WLH 2207 (Kritika)
- Tutoring hours:
- Mon 11:00 B250A (Soham)
- Wed 12:00 B240A (Kritika)
- Fri 1:00 B250A (Vineel)
- Fri 3:00 B275 (Yuncong)
- Mon 11:00 B250A (Soham)
- Final exam: Thu Mar 20, 7-10 pm
Grading
- homework (25%)
- quizzes (40%)
- final exam (35%)
Syllabus
| Tue Jan 07 | Administrivia and course overview | |
| Thu Jan 09 | Modeling uncertainty, review of probability. | |
| Tue Jan 14 | Examples of probabilistic reasoning. | HW 1 out. |
| Thu Jan 16 | Belief networks: from probabilities to graphs. | |
| Tue Jan 21 | Conditional independence, d-separation. | HW 1 due. HW 2 out. |
| Thu Jan 23 | Inference in polytrees and loopy networks. | |
| Tue Jan 28 | Learning, maximum likelihood estimation. | HW 2 due. HW 3 out. |
| Thu Jan 30 | Naive Bayes and Markov models. | |
| Tue Feb 04 | Latent variable models, EM algorithm. | HW 3 due. |
| Thu Feb 06 | Examples of EM algorithm. | |
| Tue Feb 11 | Quiz #1. | HW 4 out. |
| Thu Feb 13 | Hidden Markov models, speech recognition. | |
| Tue Feb 18 | Viterbi and forward-backward algorithms. Belief updating. | HW 4 due. HW 5 out. |
| Thu Feb 20 | Reinforcement learning. | |
| Tue Feb 25 | Markov decision processes. | HW 5 due. |
| Thu Feb 27 | Policy evaluation, improvement, and iteration. | |
| Tue Mar 04 | Quiz #2. | |
| Thu Mar 06 | Bellman optimality equation, value iteration. | HW 6 out. |
| Tue Mar 11 | Temporal difference learning, Q-learning. | |
| Thu Mar 13 | Course wrap-up, odds and ends. | HW 6 due. |
| Thu Mar 20 | Final exam |