DocumentCode
489784
Title
Learning by Smooth Simultaneous Estimation of the Error of Hypotheses
Author
Buescher, Kevin L. ; Kumar, P.R.
Author_Institution
Coordinated Science Laboratory, University of Illinois, 1101 W. Springfield Ave., Urbana, IL 61801. buescher@bellman.csl.uiuc.edu
fYear
1992
fDate
24-26 June 1992
Firstpage
2188
Lastpage
2189
Abstract
We consider the Probably Approximately Correct (PAC) model of "learning," introduced in [1]. Given data that consists of labeled samples, the problem is to select a "hypothesis" (a function) that will accurately label new samples. We investigate an approach, different from the usual one, that first estimates the error of each candidate hypothesis and then selects the hypothesis with the least estimated error.
Keywords
Contracts; Estimation error; Extraterrestrial measurements; Frequency estimation; Sampling methods; Simultaneous localization and mapping; Sufficient conditions; Zinc;
fLanguage
English
Publisher
ieee
Conference_Titel
American Control Conference, 1992
Conference_Location
Chicago, IL, USA
Print_ISBN
0-7803-0210-9
Type
conf
Filename
4792520
Link To Document