Home  |   Login  |   Logout  |   Access Information  |   Alerts  |   Purchase History  |   Cart  |   Sitemap  |   Help   
 
Abstract
BROWSE SEARCH IEEE XPLORE GUIDE SUPPORT
arrow_leftView TOC
Email/Printer Friendly Format  
 

On the sample complexity of PAC learning half-spaces against theuniform distribution

Long, P.M.  
Res. Triangle Inst., Research Triangle Park, NC ;

This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: Nov 1995
Volume: 6,  Issue: 6
On page(s): 1556-1559
ISSN: 1045-9227
References Cited: 12
CODEN: ITNNEP
INSPEC Accession Number: 5110576
Digital Object Identifier: 10.1109/72.471352
Posted online: 2002-08-06 19:47:55.0

Abstract
We prove an Ω(d/ε+1/εlog1/δ) lower bound on the PAC (probably approximately correct) learning sample complexity of learning half-spaces against the uniform distribution on the unit ball in Rd

Index Terms
Available to subscribers and IEEE members.

References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
You must log in to access:
• Advanced or Author Search
• CrossRef Search
• AbstractPlus Records
• Full Text PDF
• Full Text HTML
Login
Username
Password
» Forgot your password?
Please remember to log out when you have finished your session.
Access this document
Full Text: PDF (312 KB)
» Buy this document now
»  Learn more about
» Learn more about
Download this citation
Available to subscribers and IEEE members.
 
arrow_leftView TOC   |  Back to toparrow_up
Indexed by IEE Inspec
© Copyright 2008 IEEE – All Rights Reserved