Course Staff
Prof. Julia Hockenmaier (
)
Ruichen Wang (TA for on-campus students)
Stephen Mayhew (TA for on-campus students)
Ryan Musa (TA for online students)
You can email us directly. You can also give us anonymous feedback by filling in a form that will be emailed to Julia Hockenmaier. In that case, your name won't be revealed (but we also won't be able to reply to you directly).
Schedule
Lectures:| Tue and Thu, 3:30PM – 4:45PM | |
| 1320 Digital Computer Laboratory | |
| See Syllabus for schedule, materials and videos | |
| Julia Hockenmaier | Tue and Thu, 5:00 PM – 6:00 PM, 3324 Siebel Center | |
| TAs (on-campus students): | Mon, 1:00 PM – 3:00 PM, 1312 Siebel Center* (Stephen Mayhew) | |
| Tue, 5:00 PM – 6:00 PM, 1312 Siebel Center*† (Ryan Musa) | ||
| Wed, 9:30 AM – 11:30 AM, 1312 Siebel Center* (Ray Wang) | ||
| TAs (on-line students): | Tue, 8:00 PM – 9:00 PM (Ryan Musa) | |
| * If 1312 is not available, office hours will be held by 3407 Siebel Center (at the east end of the third floor) | ||
| † Julia's office hours on Tuesday will focus on lecture content; Ryan's will focus on homework questions |
Exams:
| Thu, March 5 in class | |
| Tue, May 5 in class | |
Announcements, general questions and discussions
If you have a question that may be of general interest to (or could even be answered by) your fellow students, you should use our Piazza site. We may also use Piazza for announcements.
Topics
The goal of machine learning is to build computer systems that can adapt and learn from their experience. Machine learning is widely used in many areas of computer science, and has become an integral component of many practical applications. In this course, we will study both the theory and application of learning methods that have proved valuable and successful in practice. The main body of the course will focus on (supervised) classification, including decision trees, linear classifiers, on-line learning algorithms, kernel based methods and probabilistic classifiers. We will also discuss ensemble methods and unsupervised learning approaches.
Objectives and Learning Goals
The objective of this class is to give students a solid introduction to the theory and practice of machine learning. At the end of this course, you will have an understanding of the theory that underlies different kinds of learning algorithms. You will also have gained practical experience with many of these algorithms, and will have implemented some of these learning algorithms yourself. If you take this course for 4 hours credit, you will also have designed your own research project in machine learning, and will have understood and evaluated a number of original research papers in machine learning that build on and go beyond the foundational material covered in class.
Assessment
There will be two closed-book exams, as well as six homework assignments. The assignments consist of theoretical and practical (programming) exercises. The Policies page describes our grading policy.
Submitting assignments and viewing your grades
We use Illinois Compass to submit assignments, and to release grade information.Textbook
There is no required textbook for this class. The Resources page contains a list of recommended books, many of which are on reserve at Grainger.
Target audience and prerequisites
Advanced undergraduates and graduates in computer science and related fields. Programming experience is necessary for the assignments. We assume knowledge of discrete math (CS 173/MATH 213), data structures (CS 225), theory of computation (CS 373), linear algebra and calculus as well as probability and statistics.