Anthony, Martin and Ratsaby, Joel (2006) Maximal width learning of binary functions. CDAM research report series, CDAM-LSE-2006-11. Centre for Discrete and Applicable Mathematics, London School of Economics and Political Science, London, UK.Full text not available from this repository.
This paper concerns learning binary-valued functions defined on IR, and investigates how a particular type of ‘regularity’ of hypotheses can be used to obtain better generalization error bounds. We derive error bounds that depend on the sample width (a notion similar to that of sample margin for real-valued functions). This motivates learning algorithms that seek to maximize sample width.
|Item Type:||Monograph (Report)|
|Additional Information:||© 2006 the authors|
|Library of Congress subject classification:||Q Science > QA Mathematics|
|Sets:||Departments > Mathematics|
Actions (login required)
|Record administration - authorised staff only|