A sufficient condition for polynomial distribution-dependent learnability


Anthony, M. and Shawe-Taylor, J. (1997) A sufficient condition for polynomial distribution-dependent learnability. Discrete Applied Mathematics, 77, (1), 1-12.

Download

Full text not available from this repository.

Description/Abstract

We investigate upper bounds on the sample-size sufficient for 'solid' learnability with respect to a probability distribution. Extending analysis of Ben-David et al. (1989, 1995) and Bendek and Itai (1991) we obtain a sufficient condition for feasible (polynomially bounded) sample-size bounds for distribution-specific (solid) learnability.

Item Type: Article
ISSNs: 0166-218X
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259794
Date Deposited: 17 Aug 2004
Last Modified: 27 Mar 2014 20:02
Further Information:Google Scholar
ISI Citation Count:1
URI: http://eprints.soton.ac.uk/id/eprint/259794

Actions (login required)

View Item View Item