Multiplicative update rules for Multilinear Support Tensor Machines

Conference paper


Kotsia, I. and Patras, I. 2010. Multiplicative update rules for Multilinear Support Tensor Machines. 20th International Conference on Pattern Recognition (ICPR 2010). Istanbul, Turkey 23 - 26 Aug 2010
TypeConference paper
TitleMultiplicative update rules for Multilinear Support Tensor Machines
AuthorsKotsia, I. and Patras, I.
Abstract

In this paper, we formulate the Multilinear Support Tensor Machines (MSTMs) problem in a similar to the Non-negative Matrix Factorization (NMF) algorithm way. A novel set of simple and robust multiplicative update rules are proposed in order to find the multilinear classifier. Updates rules are provided for both hard and soft margin MSTMs and the existence of a bias term is also investigated. We present results on standard gait and action datasets and report faster convergence of equivalent classification performance in comparison to standard MSTMs.

Research GroupResearch Group on Development of Intelligent Environments
Conference20th International Conference on Pattern Recognition (ICPR 2010)
Publication process dates
Deposited03 Dec 2012
Output statusPublished
Web address (URL)http://www.icpr2010.org/index.php
LanguageEnglish
Permalink -

https://repository.mdx.ac.uk/item/83ww6

  • 15
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as