Short Courses


Interface 2006 offers two short courses on Wednesday, May 24, 2006:


Random Graphs for Statistical Pattern Recognition
 presented by David Marchette (Naval Surface Warfare Center and George Mason University)
Time: 8:00 am to 12:00 noon.
Location: San Marino.

Abstract:

We will discuss various types of random graphs that have been suggested for pattern recognition. These include the relative neighborhood graphs of Toussaint and variations on these proposed by others; sphere graphs and digraphs; Voronoi tesselations and Delaunay triangularizations; minimum spanning trees; and nearest neighbor graphs. The use of graphs to analyze the complexity of the classification problem, provide visualization, dimensionality reduction, clustering and classification algorithms will be discussed. The various graphs and techniques will be illustrated on a wide range of interesting pattern recognition problems, as well as on simulated data sets. The material will be taken primarily from the book, Random Graphs for Statistical Pattern Recognition (by David Marchette, John Wiley & Sons, 2004).


Statistics and Information Theory
presented by Bin Yu (UC Berkeley) and Mark Hansen (UCLA)
 Time: 1:00 pm to 5:00 pm.
Location: San Marino.

Abstract:

Information Theory deals with a basic challenge in communication: How do we transmit information efficiently? In addressing that issue, Information Theorists have created a rich mathematical framework to describe communication processes with tools to characterize so-called fundamental limits of data compression and transmission.

What might Statisticians learn from Information Theory? Basic concepts like entropy and Kullback-Leibler divergence have certainly played a role in statistics. But so too have estimation frameworks like the Maximum Entropy principle; novel decompositions like ICA; and even model selection methodologies like AIC and the Principle of Minimum Description Length. In this course we will illustrate how the basic questions and tools of Information Theory relate to statistical practice and theory.


Sign up for these courses when you register. See the Registration page for fees.