Distinguished Colloquium: Vladimir Vapnik at 4:00pm on Monday, 4 December

[Margery Ishmael]

Department of Computer Science/The University of Chicago

DISTINGUISHED COLLOQUIUM

Vladimir Vapnik, AT&T Labs
Monday, 4 December at 4:00 pm in Eckhart 202
(followed by refreshments in Ryerson 255)

Title: The problem of inductive inference, statistical analysis, and 
computer learning

Abstract: In this talk I will discuss:
1. general models of inductive inference, (introduced by K. Popper),
2. theoretical models of statistical inference, (introduced by A. Kolmogorov)
3. applied (parametric) models of statistical inference (introduced by R. 
Fisher), and
4. models of inference introduced in statistical learning theory.

I will try to show that in contrast to simplified version of inference used 
in applied statistics, the principles of inference in statistical learning 
theory are development of the classical ideas of induction discussed in 
philosophy of science and theoretical models of statistics. I also will try 
to show that this implies different approaches to constructing computer 
learning algorithms.
*****
Host: Partha Niyogi


====================================================
Margery Ishmael
Department of Computer Science
1100 E. 58th St.
Chicago, IL 60637

tel: 773 834-8977  fax: 773 702-8487

marge at cs.uchicago.edu 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20001128/b7df2c08/attachment.htm