Error Bounds for Real Function Classes Based on Discretized Vapnik-Chervonenkis Dimensions

Australian National University * College of Engineering and Computer Science, Department of Computer
Publication Type:
Journal Article
Australian Journal of Intelligent Information Processing Systems, 2010, 12 (3), pp. 1 - 5
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2011001855OK.pdf519.5 kB
Adobe PDF
The Vapnik-Chervonenkis (VC) dimension plays an impor- tant role in statistical learning theory. In this paper, we propose the discretized VC dimension obtained by discretizing the range of a real function class. Then, we point out that Sauer's Lemma is valid for the discretized VC dimension. We group the real function classes having the innite VC dimension into four categories by using the discretized VC dimension. As a byproduct, we present the equidistantly discretized VC dimension by introducing an equidistant partition to segmenting the range of a real function class. Finally, we obtain the error bounds for real function classes based on the discretized VC dimensions in the PAC-learning framework.
Please use this identifier to cite or link to this item: