CSE 150.
Introduction to Artificial Intelligence:
Probabilistic Reasoning and Decision-Making
|
Subject Textbooks Meetings Assignments Syllabus Grades Lectures |
 |
 |
 |
 |
Subject
This course will introduce the mathematical 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, or Matlab. (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, Chapman and Hall, 2003.
- S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, Prentice Hall, 2003.
- R. Sutton and A. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998.
Instructors
- Professor: Lawrence Saul
- Teaching assistant: Justin Ma
Meetings
- Lectures: Wed/Fri 5:00-6:30 pm, EBU3B 2154.
- Sections: Mon 5:00-6:00 pm, EBU3B 3109
- Office hours: Mon 3:30-4:30 pm, EBU3B 4228.
Grading
- homework (30%)
- two quizzes (40%)
- final exam (30%)
Assignments
- Assignment 1 (due Wed Apr 16)
- Assignment 2 (due Wed Apr 23)
- Assignment 3 (due Wed May 07) [data]
- Assignment 4 (due Wed May 14) [data]
Tentative Syllabus
| Wed | Apr 02 | Administrivia and course overview. |
| Fri | Apr 04 | Modeling uncertainty, review of probability. |
| Wed | Apr 09 | Example of probabilistic reasoning: explaining away. |
| Fri | Apr 11 | Belief networks: from probabilities to graphs. |
| Wed | Apr 16 | Conditional independence, d-separation. |
| Fri | Apr 18 | Exact and approximate inference. |
| Wed | Apr 23 | Learning, parameter estimation, maximum likelihood. |
| Fri | Apr 25 | Quiz 1 |
| Wed | Apr 30 | Markov models of language, naive Bayes models of classification. |
| Fri | May 02 | Latent variable models, EM algorithm. |
| Wed | May 07 | Examples of EM algorithm. |
| Fri | May 09 | Hidden Markov models (HMMs), automatic speech recognition. |
| Wed | May 14 | Likelihood computation, Viterbi algorithm, belief updating. |
| Fri | May 16 | Parameter estimation in HMMs. |
| Wed | May 21 | Reinforcement learning, Markov decision processes (MDPs). |
| Fri | May 23 | Quiz 2 |
| Wed | May 28 | Policy evaluation, policy improvement. |
| Fri | May 30 | Policy iteration, value iteration. |
| Wed | Jun 04 | Temporal difference learning, Q-learning, applications. |
| Fri | Jun 06 | Course wrap-up and evaluations. |
| Fri | Jun 13 | Final exam |