CS539 - Spring 2017

CS539 Machine Learning

Syllabus— Spring 2017

WARNING: Small changes to this syllabus may be made during the semester.

COURSE DESCRIPTION:

Machine learning is an area of artificial intelligence that deals with the design and study of computer programs that are able to improve their own performance with experience, or in other words, computer programs that learn. In this graduate course we investigate different machine learning paradigms including supervised, unsupervised, and reinforcement learning. We study parametric and non-parametrid techniques, and cover multiple classification, regression, clustering, sequence analysis, meta-learning and reinforment learning techniques. Students gain extensive understanding of and experience with theoretical and practical aspects of machine learning.

For the catalog description of this course see the WPI Graduate Catalog.

CLASS MEETING:

Time: Tuesdays and Thurdays 4:00-5:20 pm
Room: SL402

INSTRUCTOR:

Prof. Carolina Ruiz

Office: FL 232
Phone Number: (508) 831-5640
Office Hours: (Held in FL 232)

Tuesdays 2-3 pm

if that time doesn't work for you or you need to see the professor more often, please email the professor to make an appointment.

TEACHING ASSISTANT (TA):

Ahmedul Kabir

Office Hours: (Held in FL A22 (FL sub-basement))

Mondays 1-2 pm

Wednesdays 3-4 pm

if you need to see Kabir at a different time, email him to schedule an appointment.

TEXTBOOK:

Required:
Alpaydin, Ethem. Introduction to Machine Learning, third edition 2014 ISBN: 9780262028189 MIT Press.

PREREQUISITE:

CS 534 Artificial Intelligence or equivalent, or permission of the instructor.

GRADES:

4 Tests (20% each):	80%
Project:	20%
Class Participation:	3%

Your final grade will reflect your own work and achievements during the course. Any type of cheating will be penalized with an F grade for the course and will be reported to the WPI Judicial Board in accordance with the Academic Honesty Policy.

Note that this course follows the guidelines established by the WPI faculty in May 2010:

"A student is expected to expend at least 56 hours of total effort for each graduate credit. This means that a student in a 3-graduate credit 14-week course is expected to expend at least 12 hours of total effort per week."

Hence, please expect to have to spend at least 9 hours of work outside the classroom on this course each week.

CLASS PARTICIPATION

Students are expected to read the material assigned for each class in advance and to participate in class discussions. Class participation will count toward students' final grades.

HOMEWORK ASSIGNMENTS, TESTS, AND PROJECT

Homework Assignments and Tests

There will be 4 homework assignments and 4 tests:

Test 1 will measure students' mastering of the material covered by HW1.
Test 2 will measure students' mastering of the material covered by HW1 and HW2.
Test 3 will measure students' mastering of the material covered by HW1, HW2 and HW3.
Test 4 will measure students' mastering of the material covered by HW1, HW2, HW3 and HW4; that is test 4 will be cumulative, measuring the students' mastering of the material covered in the entire course.

Detailed descriptions of the HW assignments will be posted to the course webpage at the appropriate times during the semester.

Project

There will be one course project. This project will include data acquisition, experimental design, programming, experimentation, and analysis of results. The project may also include assigned readings and theoretical problems. Students will be required to provide both a written report and an oral (in-class) presentation describing their work on the project.

A detailed description of the project will be posted to the course webpage at the appropriate time during the semester.

Programming Language / Environment: Matlab

For the homework assignmens, tests, project, and class demos, we will use Matlab. Matlab is available at WPI on specific computer labs around campus AND/OR via the remote desktop connection to windows.wpi.edu. A link to instructions about the remote desktop connection can be found at https://it.wpi.edu/component/id/77.

Note: only Matlab support will be provided in this course. Individual students may petition using R instead of Matlab for their project, but they will be fully responsible for dealing with R as all class demos, homework, and tests will use Matlab.

CLASS DISCUSSION FORUM AND MAILING LIST

Class Discussion Forums: The main digital venue for communication outside the classroom will be the CS539 Discussion Forums provided by Canvas. To access these discussion forums, go to Canvas, click on "Dashboard" or on "Courses", then select "MACHINE LEARNING CS539-S17-191 S17", and then click on "Discussions" on the left hand-side bar.
Class Mailing List: There are two mailing lists for this class
(replace XXX with 539 below):
- csXXX-staff@cs.wpi.edu this mailing list reaches the professor and the TA
- csXXX-all@cs.wpi.edu this mailing list reaches the entire class: professor, TA, and all students
Important:
- The "csXXX-all" mailing list will be used mainly by the professor and TA to send announcements to the whole class,
- Use the Canvas discussion forums described above to post any questions about course material, projects, tests, or assignments so that everyone benefits from the discussion - do NOT email general questions to the professor and/or TA and/or "-all" mailing list.
- Use the "csXXX-staff" mailing list above for questions that are specific to your own personal situation only.
- Don't use csXXX@cs.wpi.edu or csXXX@wpi.edu as these email addresses don't exist.
Please make sure to read Canvas CS539 discussion forums and email sent to the class mailing list constantly throughout the semester so that you don't miss any important course information.