[Sem-coll] Applied Math Colloquium on Wednesday, 1/21 at 4:40pm

Hemanshu Kaul kaul at math.iit.edu
Mon Jan 19 18:13:09 CST 2009


Hello all,

Happy New Year!!

Welcome to the Applied Math Colloquium series for Spring 2009.

Our first talk this semester will be in two days on Wednesday, 21st 
January at 4:40pm. The speaker is Partha Niyogi from the Computer Science 
and Statistics departments at the University of Chicago. Professor Niyogi 
works in pattern recognition and machine learning problems that arise in 
the computational study of human speech and language. The title of his 
talk is "A geometric perspective on machine learning and algorithms". The 
abstract is given below.

As usual the talk will be given in room 106 in E1 building, and 
refreshments will be served at 4:30pm.

Please bookmark http://www.iit.edu/csl/am/colloquia/ for the latest 
schedule of the colloquium and other Applied Math seminars. As you can see 
in the announced schedule, most of the colloquiua will be given on Mondays 
but a few talks will be on Wednesdays.

Looking forward to seeing you on Wednesday.

Hemanshu

-------------------------------------------
Title:  A geometric perspective on machine learning and algorithms
Speaker: Partha Niyogi, University of Chicago

When and Where: 106, E1 Bldg; 4:30pm Wednesday, 1/21.

Abstract: Increasingly, we face machine learning problems in very high
dimensional spaces. We proceed with the intuition that although
natural data lives in very high dimensions, they have relatively few
degrees of freedom. One way to formalize this intuition is to model
the data as lying on or near a low dimensional manifold embedded in
the high dimensional space. This point of view leads to a new class of
algorithms that are "manifold motivated" and a new set of theoretical
questions that surround their analysis. A central construction in
these algorithms is a graph or simplicial complex that is data-derived
and we will relate the geometry of these to the geometry of the
underlying manifold. Applications to data analysis, machine
learning, and numerical computation will be considered.

-------------------------------

_______________________________________________________________
Hemanshu Kaul
Assistant Professor of Applied Mathematics
Illinois Institute of Technology, Chicago
http://www.iit.edu/csl/am/faculty/kaul_hemanshu.shtml
---------------------------------------------------------------


More information about the seminar-coll mailing list