Constant Rate Approximate Maximum Margin Algorithms


Tsampouka, Petroula and Shawe-Taylor, John (2006) Constant Rate Approximate Maximum Margin Algorithms.

Download

[img] PDF
Download (215Kb)

Description/Abstract

We present a new class of perceptron-like algorithms with margin in which the “effective” learning rate, defined as the ratio of the learning rate to the length of the weight vector, remains constant. We prove that the new algorithms converge in a finite number of steps and show that there exists a limit of the parameters involved in which convergence leads to classification with maximum margin.

Item Type: Monograph (Technical Report)
Keywords: online learning, maximum margin classifiers
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 261832
Date Deposited: 26 Jan 2006
Last Modified: 27 Mar 2014 20:04
Further Information:Google Scholar
ISI Citation Count:1
URI: http://eprints.soton.ac.uk/id/eprint/261832

Actions (login required)

View Item View Item