BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The weighted p-Laplacian and semi-supervised learning - Jeff Calde
 r (University of Minnesota)
DTSTART:20171103T145000Z
DTEND:20171103T154000Z
UID:TALK94435@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Semi-supervised learning refers to machine learning algorithms
  that make use of both labeled data and unlabeled data for learning tasks.
  Examples include large scale nonparametric regression and classification 
 problems\, such as predicting voting preferences of social media users\, o
 r classifying medical images. In today&#39\;s big data world\, there is an
  abundance of unlabeled data\, while labeled data often requires expert la
 beling and is expensive to obtain. This has led to a resurgence of semi-su
 pervised learning techniques\, which use the topological or geometric prop
 erties of large amounts of unlabeled data to aid the learning task. In thi
 s talk\, I will discuss some new rigorous PDE scaling limits for existing 
 semisupervised learning algorithms and their practical implications. I wil
 l also discuss how these scaling limits suggest new ideas for fast algorit
 hms for semi-supervised learning.&nbsp\;
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR