To improve the training speed of SVM, we propose a new SVM training approach which takes thick convex-hull as training set. The approach makes better use of the margin information for classification of data sets, and thus extends the use of convex hull to approximately linearly separable problems. Experiments on 5 UCI data sets indicate that the approach speeds up training of SVM with guarantee of generalization accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fast SVM Training Based on Thick Convex-hull


    Contributors:
    Zhang, Hong-da (author) / Wang, Xiao-dan (author) / Xu, Hai-Long (author) / Li, Yan-lei (author) / Quan, Wen (author)


    Publication date :

    2008-05-01


    Size :

    393714 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast component labelling and convex hull computation on reconfigurable meshes

    Olariu, S. / Schwing, J. L. / Zhang, J. | British Library Online Contents | 1993


    Wiggle hull design having a concave and convex planing hull

    ALMETER JOHN | European Patent Office | 2016

    Free access


    Multivariate Fault Detection with Convex Hull

    Luo, M. / IEEE / AIAA | British Library Conference Proceedings | 2004


    Detecting textured objects using convex hull

    Lu, K. / Pavlidis, T. | British Library Online Contents | 2007