Directory of Classes
NOTE: Course information changes frequently. Please re-visit these pages periodically for the most recent and up-to-date information.

Fall 2017 Electrical Engineering and Computer Science E6720 section 001
BAYESIAN MOD MACHINE LEARNING

Call Number 10226
Day & Time
Location
R 4:10pm-6:40pm
301 Pupin Laboratories
Points 3
Approvals Required None
Instructor John W Paisley
Type LECTURE
Course Description Prerequisites: Basic calculus, linear algebra, probability, and programming. Basic statistics and machine learning strongly recommended. Bayesian approaches to machine learning. Topics include mixed-membership models, latent factor models, Bayesian nonparametric methods, probit classification, hidden Markov models, Gaussian mixture models, model learning with mean-field variational inference, scalable inference for Big Data. Applications include image processing, topic modeling, collaborative filtering and recommendation systems.
Web Site CourseWorks
Department Electrical Engineering
Enrollment 125 students (200 max) as of 12:15AM Saturday, November 18, 2017
Final Exam Day/Time
R 4:10pm-7:00pm
Final Location 428 Pupin Laboratories
Subject Electrical Engineering and Computer Science
Number E6720
Section 001
Division School of Engineering and Applied Science: Graduate
Open To Engineering and Applied Science: Graduate, Graduate School of Arts and Science, Engineering and Applied Science: Undergraduate
Campus Morningside
Section key 20173EECS6720E001

Home      About This Directory      Online Bulletins      ColumbiaWeb      SSOL
SIS update 11/18/17 00:15    web update 11/18/17 15:09