EECS 445 - Introduction to Machine Learning
Section: 001
Term: WN 2018
Subject: Electrical Engineering and Computer Science (EECS)
Department: CoE Electrical Engineering and Computer Science
Credits:
4
Requirements & Distribution:
BS
Enforced Prerequisites:
EECS 281, completed with a minimum grade of C or better.
Advisory Prerequisites:
MATH 214 or equivalent; STATS 250 or equivalent.
BS:
This course counts toward the 60 credits of math/science required for a Bachelor of Science degree.
Repeatability:
May not be repeated for credit.

Theory and implementation of state of the art machine learning algorithms for large-scale real-world applications. Topics include supervised learning (regression, classification, kernal methods, neural networks, and regularization) and unsupervised learning, (clustering, density estimation, and dimensionality and reduction).

EECS 445 - Introduction to Machine Learning
Schedule Listing
001 (LEC)
 
28375
Open
90
 
-
MW 4:30PM - 6:00PM
Note: STUDENTS MUST ELECT DISCUSSION AND LECTURE SECTIONS.Course will open to EE UG and ECE Grad who meet course prerequisites on Wednesday, December 6, 2017.
011 (DIS)
P
24198
Open
30
 
-
F 11:30AM - 12:30PM
012 (DIS)
P
26321
Open
30
 
-
F 10:30AM - 11:30AM
013 (DIS)
P
26322
Open
30
 
-
F 12:30PM - 1:30PM
NOTE: Data maintained by department in Wolverine Access. If no textbooks are listed below, check with the department.
Syllabi are available to current LSA students. IMPORTANT: These syllabi are provided to give students a general idea about the courses, as offered by LSA departments and programs in prior academic terms. The syllabi do not necessarily reflect the assignments, sequence of course materials, and/or course expectations that the faculty and departments/programs have for these same courses in the current and/or future terms.

No Syllabi are on file for EECS 445. Click the button below to search for a different syllabus (UM login required)

Search for Syllabus
The CourseProfile (ART) system, supported by the U-M Provost’s 3rd Century Initiative through a grant to the Digital Innovation Greenhouse, provides additional information about: course enrollments; academic terms and instructors; student academic profiles (school/college, majors), and previous, concurrent, and subsequent course enrollments.

CourseProfile (ART)