Affordable Access

Publisher Website

An iterative algorithm learning the maximal margin classifier

Authors
Journal
Pattern Recognition
0031-3203
Publisher
Elsevier
Publication Date
Volume
36
Issue
9
Identifiers
DOI: 10.1016/s0031-3203(03)00060-8
Keywords
  • Pattern Recognition
  • Linear Classifier
  • Supervised Learning
  • Support Vector Machines
  • Kernel Functions
Disciplines
  • Computer Science

Abstract

Abstract A simple learning algorithm for maximal margin classifiers (also support vector machines with quadratic cost function) is proposed. We build our iterative algorithm on top of the Schlesinger–Kozinec algorithm (S–K-algorithm) from 1981 which finds a maximal margin hyperplane with a given precision for separable data. We suggest a generalization of the S–K-algorithm (i) to the non-linear case using kernel functions and (ii) for non-separable data. The requirement in memory storage is linear to the data. This property allows the proposed algorithm to be used for large training problems. The resulting algorithm is simple to implement and as the experiments showed competitive to the state-of-the-art algorithms. The implementation of the algorithm in Matlab is available. We tested the algorithm on the problem aiming at recognition poor quality numerals.

There are no comments yet on this publication. Be the first to share your thoughts.