The Kernel Adatron With Bias Unit: Analysis of the Algorithm (Part 1)
Thilo-Thomas Frieb, Robert F. Harrison · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · 1998
The Kernel Adatron with bias allows to find a large margin classifier in the kernel feature space. It is an adaptive perceptron (Adatron) which uses augmented patterns in the kernel feature space. The algorithm has been proposed firstly in [9]. In this document the convergence of properties are investigated. As a by-product of the current analysis a simpler formulation of the algorithm is derived.