Open Access Open Access  Restricted Access Subscription or Fee Access

Support Vector Machine Model for the Key Issues of Parameters Selection

Xilong Qu, Hao Zhongxiao

Abstract


Take estimate of VC dimension as the research object, in this base estimate the bound of generalization ability of learning machine, for the structure problem of sample linear separable in the feature space, deploy thorough discussion on high efficiency solving model choice problem, looking forward to come out some useful research results, to promote the further development of SVM in the theory and industrial applications. The study is a hot issue which internationally recognized, including: function sets the estimate of VC dimension; upper bound estimate of tight generalization error; the relationship of scale parameter and regularization factor in RBF nucleus; model parameter speediness selection strategies based on optimization algorithm. Inspired by the clustering method, a method of Pre-Selection Samples based on Class Centroid(PSCC) in a high-dimensional feature space is proposed. This method overcomes the curse of dimensionality samples, and improves the training efficiency.

Keywords


support vector machine; model; parameter selection

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.