Alexandros Karatzoglou, Alex Smola, Achim Zeileis, Kurt Hornik
kernlab - A Kernel Methods Package
**************************************************************

Designing software for Support Vector Machines (SVM) and kernel methods in
general poses an interesting design problem. Our aim is to provide one possible
solution using R object oriented features. kernlab is an extensible, object
oriented, package for kernel-based learning in R. Its main objective is to
provide a tool kit consisting of basic kernel functionality, optimizers and
high level kernel algorithms which can be extended by the user in a very
modular way and tries to solve some of the design problems posed by this kind
of software. Based on this infrastructure kernel-based methods can easily be
constructed and developed.