The STUDIA UNIVERSITATIS BABEŞ-BOLYAI issue article summary

The summary of the selected article appears at the bottom of the page. In order to get back to the contents of the issue this article belongs to you have to access the link from the title. In order to see all the articles of the archive which have as author/co-author one of the authors mentioned below, you have to access the link from the author's name.

  
       
         
    STUDIA INFORMATICA - Issue no. Sp.Issue%201 / 2009  
         
  Article:   SEMI-SUPERVISED FEATURE SELECTION WITH SVMS.

Authors:  ZALÁN BODÓ, ZSOLT MINIER. 		 
       
         
  Abstract:   Feature selection plays and important role in machine learning: eliminates irrelevant dimensions thus turning the learner into a better, more efficient system. In this paper we use non-linear semi-supervised SVMs for feature selection and through experiments we demonstrate the efficiency of the methods, showing how unlabeled data can lead to a better reduction. Semi-supervised feature selection is achieved by using semi-supervised/cluster kernels, that is embedding the information provided by the unlabeled data into the kernel, andapplying dimensionality reduction methods developed for non-linear SVMs.

Key words and phrases. semi-supervised learning, feature selection, kernel methods. 		 
         
     
         
         
      Back to previous page