Motivation and Background
Epsilon covers were introduced in calculus. So we provide here a very general definition.
Definition
Let \((M,\varrho )\) be a metric space, let S ⊆ M, and let ɛ > 0. A set E ⊆ M is an ɛ -cover for S, if for every s ∈ S there is an e ∈ E such that ϱ(s, e) ≤ ɛ.
An ɛ -cover E is said to be proper, if E ⊆ S.
Application
The notion of an É›-cover is frequently used in kernel-based learning methods.
For further information, we refer the reader to Herbrich (2002).
Cross-References
This is a preview of subscription content, log in via an institution to check access.
Recommended Reading
Herbrich R (2002) Learning kernel classifiers: theory and algorithms. MIT, Cambridge
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Zeugmann, T. (2014). Epsilon Cover. In: Sammut, C., Webb, G. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7502-7_82-1
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7502-7_82-1
Received:
Accepted:
Published:
Publisher Name: Springer, Boston, MA
Online ISBN: 978-1-4899-7502-7
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering