School on Principles of Nonparametric Learning

[Nicolo` Cesa-Bianchi]

                      Principles of Nonparametric Learning 

                        Udine (Italy), July 9-13, 2001

                        Advanced School coordinated by

                                  L. Gyrfi
                Budapest University of Technology and Economics
                                   Hungary


Modern nonparametric methods have become the most important tools in
various fields of applications of pattern recognition, density and
regression function estimation, data compression, on-line learning and
prediction. The common feature in these problems is that some unknown
underlying system generates data and the best action is to be learnt
from these data.

The purpose of the course is to teach the basic principles of
nonparametric inference with emphasis on the cited areas. Leading
international experts of these areas will introduce the participants
into the theory and advanced methods of inference.

A prototype problem to be discussed in depth is the problem of pattern
recognition in which an observation is to be classified into one of a
finite number of classes. The optimal classification must be
approximated based on training data. Classical nonparametric methods
such as nearest neighbor and kernel methods, as well as modern
methodologies including neural networks, support vector machines, and
binary tree classifiers will be studied in the course. Evolutionary
optimization methodologies, e.g. genetic programming, will also be
considered as they allow nonparametric learning to handle complex data
and explore structured model spaces.

The methodologies covered by this course have found applications in
various fields such as identification of biological and mechanical
systems, data mining, forecasting, universal data compression, optimal
portfolio strategies for stock markets, and measurement-based call
admission control for high-speed communication networks.

The course is addressed to postgraduates in engineering, mathematics,
and computer science, and researchers in universities and research
institutions.

Please visit the school home page (www.cism.it/c2001/c03/) for
information on program, admission, and accomodation.