| CSE 150 - Winter 2015 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:
Hannah Chen (hecheneng.ucsd.edu)
Liam Fedus (wfedusucsd.edu)
Kristjan Jonsson (kjonssoneng.ucsd.edu)
Mohit Kothari (mkotharieng.ucsd.edu)
Soham Shah (srshaheng.ucsd.edu)
Huaipeng Zhang (huz021eng.ucsd.edu)
- Tutors:
Xiaoyu (Justin) Liu (x4liuucsd.edu)
Ruiqing (Raymond) Qiu (rqiuucsd.edu)
Max Shen (mshenucsd.edu)
Zhen Zhai (zzhaiucsd.edu)
Meetings
- Lectures: Tue/Thu 2:00-3:20 pm, Center 101.
- Office hour: Fri 9-10 am, EBU3B-3214.
- Discussion sections:
- Mon 5-6 pm, WLH 2207 (Kristjan)
- Mon 7-8 pm, Center 109 (Huaipeng)
- Thu 6-7 pm, Center 222 (Soham)
- Fri 3-4 pm, WLH 2209 (Liam)
- Fri 5-6 pm, Center 105 (Hannah)
- Fri 6-7 pm, Center 105 (Mohit)
- Mon 5-6 pm, WLH 2207 (Kristjan)
- Tutoring hours in CSE basement:
- Mon 2-3:30 pm, 8-9:30 pm (Max)
- Tue 10-11 am, Thu 12-2 pm (Zhen)
- Mon 9-11 am, Sat 4-6 pm (Raymond)
- Fri 12:30-3:30 pm (Justin)
- Mon 2-3:30 pm, 8-9:30 pm (Max)
- Final exam: Thu Mar 19, 3-6 pm
Grading
- homework (25%)
- quizzes (40%)
- final exam (35%)
Syllabus
| Tue Jan 06 | Administrivia and course overview. | |
| Thu Jan 08 | Modeling uncertainty, review of probability. | |
| Tue Jan 13 | Examples of probabilistic reasoning. | HW 1 out. |
| Thu Jan 15 | Belief networks: from probabilities to graphs. | |
| Tue Jan 20 | Conditional independence, d-separation. | HW 1 due. HW 2 out. |
| Thu Jan 22 | Inference in polytrees and loopy networks. | |
| Tue Jan 27 | Learning, maximum likelihood estimation. | HW 2 due. HW 3 out. |
| Thu Jan 29 | Naive Bayes and Markov models. | |
| Tue Feb 03 | Latent variable models, EM algorithm. | HW 3 due. |
| Thu Feb 05 | Examples of EM algorithm. | |
| Tue Feb 10 | Quiz #1. | HW 4 out. |
| Thu Feb 12 | Hidden Markov models, speech recognition. | |
| Tue Feb 17 | Viterbi and forward-backward algorithms. Belief updating. | HW 4 due. HW 5 out. |
| Thu Feb 19 | Reinforcement learning. | |
| Tue Feb 24 | Markov decision processes. | HW 5 due. |
| Thu Feb 26 | Policy evaluation, improvement, and iteration. | |
| Tue Mar 03 | Quiz #2. | HW 6 out. |
| Thu Mar 05 | Bellman optimality equation, value iteration. | |
| Tue Mar 10 | Temporal difference learning, Q-learning. | |
| Thu Mar 12 | Course wrap-up, odds and ends. | HW 6 due. |
| Thu Mar 19 | Final exam |