Henry S. Baird    Spring 2012 Course


Machine Learning Seminar

CSE 498/398   (3 credits)

CRNs: 17233 (498); 17232 (398)


Note to CS Ph.D. Graduate Students:  this course fulfills two 'Core Areas':  (1) Computer Applications, and (2) Theory.

Note to advanced undergraduates:  you are very welcome in this course with permission of the Instructor; you'll be expected to participate in classroom discussions and to present a literature review talk in class, exactly as the grad students do; but you may choose an easier (e.g. shorter) final project.

An introduction to topics at the research frontier of machine learning and pattern recognition, including most of the following:

• Supervised, unsupervised, & semi-supervised fitting of statistical models to data;
  

• Training of classifiers including Bayesian, parametric, nonparametric, neural nets, support vector machines, & classification trees;

• Probabilistic graphical models, kernel methods, combination, randomization, boosting, & bootstrapping;

• Adaptive (non-stationary) learning & anytime algorithms; and

• General methodological issues, including best practices for statistical training and testing, the curse of dimensionality, & feature selection.
  

Brief lectures by the instructor; weekly assigned readings in the research literature (no textbook); no examinations.  Students will be evaluated on their:

1. informed and thoughtful participation in the frequent in-class discussions of the assigned reading (for this reason, attendance is required at all class meetings);
2. short but professional in-class presentations summarizing and analyzing selected technical articles, book chapters etc; and
3. final projects tailored to the interests of each student, either experimental, scholarly, or analytical (mathematical), including a 15-25 page professionally written report.

Course Objective:  On completing this course, students will be sufficiently familiar with the theory, notation, and vocabulary of machine learning and pattern recognition to be able to pursue matters of interest in the current technical literature. They will also have a grasp of key engineering issues arising in applications.

Meetings: Tuesdays/Thursdays, 10:45 AM - 12:00 noon, in Maginnes classroom 480.

Instructor: Prof. Henry Baird, hsb2@lehigh.edu. Office:  Packard Lab 380.   Office Hours: Wednesdays 12:10-1:00 PM, or by appointment.

CourseSite We will use CourseSite website CSE-398/CSE-498-Machine Learning-SP12 to distribute assigned readings, lecture slides, project assignments, and grades.  As soon as you are enrolled in this course, please browse coursesite.lehigh.edu and try to login:  if you cannot, send email to the instructor.

Prerequisites:

• CSE 340:  Algorithms---or comparable background in basic algorithms and data structures.
• Math 205: Linear Algebra etc---or familiarity with linear algebra & matrices.
• Math 231 or Math 309 or CSC 450: Applied Probability & Statistics---or some background in discrete probability and applied statistics & data analysis.
• CSE 109: Programming in C++---or enough experience with C++, Java, C, or (even better) MatLab to complete a small software project without faculty supervision.
• Other relevant background (helpful, but not required): Artificial Intelligence, Computer & Robot Vision, Data Mining, Web Data Analysis, Bioinformatics, Reinforcement Learning.

If you have any questions, ask the instructor: Henry Baird, hsb2@lehigh.edu.

Accommodations for Students with Disabilities:  If you have a disability for which you are or may be requesting accommodations, please contact both your instructor and the Office of Academic Support Services, University Center C212 (610-758-4152) as early as possible in the semester.  You must have documentation from the Academic Support Services office before accommodations can be granted.