Course Information: Introduction to Machine Learning

An investigation of programs that can dynamically adapt their behavior. The course focuses on two main general ideas: supervised learning and unsupervised learning. In supervised learning, a set of already-known correct responses to already-seen inputs is provided, and is used to train the program to make correct responses to new inputs. For instance, a facial recognition program could be supplied with a number of photographs, each labeled with the name of the person in the image, and learn to recognize new images of those persons. In unsupervised learning, a program seeks to find hitherto unknown patterns in data, without any pre-judgment about what those patterns might be. For example, a music recommendation program might try to find similarities between groups of songs, so that when a user likes one such song, others in its similar group can be recommended to them. The course looks at various computational and mathematical models and techniques that can be applied to such problems.

Class information page:
Piazza discussion forum:

Prerequisites: COMP 15 and COMP/MATH 22 or 61 or consent of instructor. (COMP 160 is highly recommended).
See the syllabus section of this site for more discussion of expected competencies.

Textbook: No textbook purchase is required. We will be using a number of online resources, accessible freely by browser and/or in PDF form; details can be found in the syllabus section of this site.

Instructor: Marty Allen
(Note: due to the large size of this class, excessive email traffic is discouraged. Please use the email address given only if absolutely necessary. Email will not be used for answering questions in detail; instead try instructor or TA office hours, and the class Piazza page.)

Office: 237 Halligan Hall
Office Hours: Tuesday, 11:00 AM – 1:00 PM

Class Location: 253 Robinson Wing, SEC
Time: (Mon/Wed) 4:30 – 5:45 PM

Teaching Assistants (office hours click here):
Mike Pietras
Simon Mattssonn
Darren Ting
Billy Whitrock