Multi-category classifiers and sample width

Martin Anthony; Joel Ratsaby

doi:10.1016/j.jcss.2016.04.003

Multi-category classifiers and sample width

Martin Anthony, Joel Ratsaby

Department of Electrical and Electronics Engineering

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are multi-category and are defined on some arbitrary metric space.

Original language	English
Pages (from-to)	1223-1231
Number of pages	9
Journal	Journal of Computer and System Sciences
Volume	82
Issue number	8
DOIs	https://doi.org/10.1016/j.jcss.2016.04.003
State	Published - 1 Dec 2016

Keywords

Generalization error
Machine learning
Multi-category classification
Pattern recognition

Access to Document

10.1016/j.jcss.2016.04.003

Cite this

@article{573139f532a3457984b6a0e48e8166c0,

title = "Multi-category classifiers and sample width",

abstract = "In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are multi-category and are defined on some arbitrary metric space.",

keywords = "Generalization error, Machine learning, Multi-category classification, Pattern recognition",

author = "Martin Anthony and Joel Ratsaby",

note = "Publisher Copyright: {\textcopyright} 2016 Elsevier Inc.",

year = "2016",

month = dec,

day = "1",

doi = "10.1016/j.jcss.2016.04.003",

language = "אנגלית",

volume = "82",

pages = "1223--1231",

journal = "Journal of Computer and System Sciences",

issn = "0022-0000",

publisher = "Academic Press Inc.",

number = "8",

}

TY - JOUR

T1 - Multi-category classifiers and sample width

AU - Anthony, Martin

AU - Ratsaby, Joel

PY - 2016/12/1

Y1 - 2016/12/1

N2 - In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are multi-category and are defined on some arbitrary metric space.

AB - In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are multi-category and are defined on some arbitrary metric space.

KW - Generalization error

KW - Machine learning

KW - Multi-category classification

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=84977101024&partnerID=8YFLogxK

U2 - 10.1016/j.jcss.2016.04.003

DO - 10.1016/j.jcss.2016.04.003

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:84977101024

SN - 0022-0000

VL - 82

SP - 1223

EP - 1231

JO - Journal of Computer and System Sciences

JF - Journal of Computer and System Sciences

IS - 8

ER -

Multi-category classifiers and sample width

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this