CSE 5522: Survey of Artificial Intelligence II: Advanced Techniques

This course provides an overview of modern statistical AI, including probability and statistics, graphical models, and machine learning. The course also includes applications to computer vision, natural language processing, information retrieval, and speech processing.

There is no official textbook, however, the following books are relevant to the material. The Russell and Norvig book is the one traditionally used for the class.

Grading will be based on:

Homeworks (30%)

The homeworks will include both written and programming assignments. For programming asignments, include a README, and make sure your code is easy to run following the instructions. Homework should be submitted to a Dropbox folder which will be set up in Carmen by 11:59pm on the day it is due. Late homework will be accepted up to 48 hours later for 50% credit. After 48 hours, late homework will not be accepted. Please email your homework to the instructor if there are any technical issues with submission.

midterm + final (40%)

The midterm will be in class on March 5th. The final is scheduled for Monday May 4 from 10am - 11:45. Each will be worth 20% of the grade, for a total of 40%.

Projects (30%)

The project is an open-ended assignment, with the goal of gaining experience applying the techniques presented in class to real-world datasets. Students will work in groups of 2-4. Examples projects can be found Here. It is a good idea to run your planned project by the instructor to get feedback before beginning work on experiments. The final project report should be 4 pages and is due on April 30. The report should describe the problem you are solving, what data is being used, the proposed techique you are applying in addition to what baseline is used to compare against. You can use any software for the project, including off-the-shelf machine learning toolkits, for example Scikit-Learn, or if you prefer you can implement one of the algorithms we have disucssed in class.

  • Homework 1 (Due Feb. 5) Data: wine.train, wine.test, wine.true for more details on the data see: UCI Wine Data
  • Homework 2 (Due March 3 before class)
  • Homework 3 (Due April 14 before class)
  • Schedule
    Date Topic Reading
    1/13 Course Overview No Reading
    1/15 Probability Theory Review (R+N Ch 13, K+F Ch 2)
    1/20 Statistical Estimation (K+F Ch 17, R+N Ch 20, Notes on Parameter Estimation (Sections 1-3 are relevant))
    1/22 Mixture Models and the EM Algorithm (R+N Chapter 20, Murphy Ch 11, K+F Chapter 19)
    1/27 Hidden Markov Models (PDF) (R+N Chapter 15, Murphy Ch 17, Notes on HMMs)
    1/29 No Class (AAAI)
    2/10 Bayesian Networks (PDF) (R+N Chapter 14, Murphy Chapter 10, K+F Chapter 3)
    2/12 Markov Networks (PDF) (Murphy Chapter 19, K+F Chapter 4)
    2/16 Exact Inference (PDF) (Murphy Chapter 20, R+N Chapter 14
    2/16 Junction Trees (PDF) (Murphy Chapter 20, R+N Chapter 14
    3/3 Midterm Review
    3/10 Sampling-Based Inference R+N Chapter 14, K+F Chapter 11
    3/12 Learning Bayesian Networks Murphy Chapter 10+26, K+F Chapters 17+18
    3/24 Learning Markov Networks Murphy Chapter 19, K+F Chapter 20
    3/26 Learning Markov Networks Murphy Chapter 19, K+F Chapter 20
    3/31 Decision Theory R+N Chapter 16, K+F Chapter 22
    4/2 Markov Decision Processes R+N Chapter 17 and 21, K+F Chapter 23
    4/7 No Class
    4/9 Speech and Language Processing Russel + Norvig Chapters 22+23
    4/14 Speech and Language Processing
    4/16 Guest Lectures Orton Hall 110
    4/21 Guest Lectures Schoenbaum Hall 330
    4/23 Guest Lectures Orton Hall 110
    5/4 Final (10-11:45am) Final Review