| CSE 150 - Summer 2016 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:
Zhen Zhai (zzhaiucsd.edu)
Sahil Agarwal (saa034eng.ucsd.edu)
Meetings
- Lectures: Tue/Thu 11:00a-1:50p, WLH 2005.
- Office hour: Mon/Fri 9:00a, CSE 3214.
- Discussion sections in CSE 2154: Wed 11a (Zhen), Fri 11a (Sahil)
- Tutoring hours in CSE 4262: Thu 2:30p (Zhen), Mon 11a (Sahil)
- Final exam: Sat July 30, 11:30a-2:30p
Grading
- homework (54%)
- final exam (46%)
Syllabus
| Tue June 28 | Administrivia and course overview. Modeling of uncertainty, review of probability. | |
| Thu June 30 | Examples of probabilistic reasoning. Belief networks: from probabilities to graphs. | HW 2 |
| Tue July 05 | Conditional independence, d-separation. Inference in polytrees and loopy networks. | HW 3 |
| Thu July 07 | Learning, maximum likelihood estimation. Naive Bayes and Markov models. | HW 4 |
| Tue July 12 | Latent variable models, EM algorithm. Examples: noisy-OR, word clustering. | HW 5 |
| Thu July 14 | Hidden Markov models, automatic speech recognition. Inference and learning in HMMs. | HW 6 |
| Tue July 19 | Introduction to reinforcement learning. Markov decision processes. | HW 7 |
| Thu July 21 | Policy evaluation, greedy policies, policy improvement. | HW 8 |
| Tue July 26 | Policy and value iteration. Temporal difference learning, Q-learning. | HW 9 |
| Thu July 28 | Course wrap-up, odds and ends, review. | |
| Sat July 30 | Final exam |