Two Announcements on Support Vector Machines

[Chris Burges]

TUTORIAL:

The following paper is available at

    http://svm.research.bell-labs.com/SVMdoc.html


A Tutorial on Support Vector Machines for Pattern Recognition

C.J.C. Burges, Bell Laboratories, Lucent Technologies

Invited Paper for Database Mining and Knowledge Discovery 

The tutorial starts with an overview of the concepts of VC dimension and
structural risk minimization.  We then describe linear Support Vector Machines
(SVMs) for separable and non-separable data, working through a non-trivial
example in detail.  We describe a mechanical analogy, and discuss when SVM
solutions are unique and when they are global.  We describe how support vector
training can be practically implemented, and discuss in detail the kernel
mapping technique which is used to construct SVM solutions which are non-linear
in the data.  We show how Support Vector machines can have very large (even
infinite) VC dimension by computing the VC dimension for homogeneous polynomial
and Gaussian radial basis function kernels; we then show how SVMs nevertheless
provide a natural mechanism for implementing structural risk minimization, often
resulting in good generalization performance.  Finally, we discuss the various
bounds on the generalization performance of SVMs.  We give numerous examples and
proofs of most of the key theorems.  There is new material, and I hope that the
reader will find that even old material is cast in a fresh light.


                          *     *     *


SUPPORT VECTOR MACHINE WEB PAGE: 

The following page allows users to submit their data, and have a support vector
machine (SVM) trained automatically on that data.  The results, as well as
automatically generated ANSI C code which instantiates their classifier, are
then available to them via FTP.  There are also other resources available (for
example, an Applet which allows users to play with two-dimensional SVM pattern
recognition).  The URL is:

      http://svm.research.bell-labs.com