Skip to main navigation Skip to search Skip to main content

Automatic view composition for improving co-training

  • Sungkyunkwan University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we propose a view composition method for co-training. In order to compose views properly, two assumptions should be satisfied. One is that two views are class-conditionally independent on each other; the other is that the classification information between labels and view is high. We apply Class-Conditional Independent Component Analysis (CC-ICA) to obtain new features which are mutually independent, and compose views hold a high classification information. We show that our method is promising and effective through the experiment.

Original languageEnglish
Title of host publication2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages13-16
Number of pages4
ISBN (Electronic)9781479959556
DOIs
StatePublished - 18 Feb 2014
Externally publishedYes
Event2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 - Kitakyushu, Japan
Duration: 3 Dec 20146 Dec 2014

Publication series

Name2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014

Conference

Conference2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
Country/TerritoryJapan
CityKitakyushu
Period3/12/146/12/14

Keywords

  • CC-ICA
  • co-training
  • mutual information
  • view composition

Fingerprint

Dive into the research topics of 'Automatic view composition for improving co-training'. Together they form a unique fingerprint.

Cite this