Department of
Epidemiology &

Genetic Epidemiology

Global Health

Behavior and Prevention

Health Care

Modern Biostatistics

Biostatistics Seminar

We recommend the following related seminar at EECS


11:30am -- White 411

Title:Manifold and Semi-supervised learning

Speaker: Prof. Mikhail Belkin, Ohio State University

Abstract: In this talk I will discuss the role of geometric structures in machine learning, which have been an active topic of development in recent years. It turns out that certain geometric assumption about the shape of the probability distribution can be utilized to create families of data-dependent regularizers, and to develop algorithms for unsupervised and semi-supervised learning. I will talk about the ideas, the resulting algorithms and applications and some theoretical results underlying these methods.

Hosting: Ilimitada Hosting Chile VPS