Learnability: Admissible, co-finite, and hypersimple languages

Ganesh Baliga; John Case

doi:10.1006/jcss.1996.0047

Learnability: Admissible, co-finite, and hypersimple languages

Ganesh Baliga, John Case

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

4 Scopus citations

Abstract

Presented is a surprising characterization of hypersimple sets in algorithmic learning theory. It is used herein to obtain an elegant, tight separation result for learnability criteria. It is argued that such separation results may yield insight for eventual characterizations.

Original language	English (US)
Pages (from-to)	26-32
Number of pages	7
Journal	Journal of Computer and System Sciences
Volume	53
Issue number	1
DOIs	https://doi.org/10.1006/jcss.1996.0047
State	Published - Aug 1996
Externally published	Yes

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
General Computer Science
Computer Networks and Communications
Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1006/jcss.1996.0047

Cite this

@article{d5f6c22a34874e23a105c5b779d6a62c,

title = "Learnability: Admissible, co-finite, and hypersimple languages",

abstract = "Presented is a surprising characterization of hypersimple sets in algorithmic learning theory. It is used herein to obtain an elegant, tight separation result for learnability criteria. It is argued that such separation results may yield insight for eventual characterizations.",

author = "Ganesh Baliga and John Case",

year = "1996",

month = aug,

doi = "10.1006/jcss.1996.0047",

language = "English (US)",

volume = "53",

pages = "26--32",

journal = "Journal of Computer and System Sciences",

issn = "0022-0000",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Learnability

T2 - Admissible, co-finite, and hypersimple languages

AU - Baliga, Ganesh

AU - Case, John

PY - 1996/8

Y1 - 1996/8

N2 - Presented is a surprising characterization of hypersimple sets in algorithmic learning theory. It is used herein to obtain an elegant, tight separation result for learnability criteria. It is argued that such separation results may yield insight for eventual characterizations.

AB - Presented is a surprising characterization of hypersimple sets in algorithmic learning theory. It is used herein to obtain an elegant, tight separation result for learnability criteria. It is argued that such separation results may yield insight for eventual characterizations.

UR - http://www.scopus.com/inward/record.url?scp=0030219360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030219360&partnerID=8YFLogxK

U2 - 10.1006/jcss.1996.0047

DO - 10.1006/jcss.1996.0047

M3 - Article

AN - SCOPUS:0030219360

SN - 0022-0000

VL - 53

SP - 26

EP - 32

JO - Journal of Computer and System Sciences

JF - Journal of Computer and System Sciences

IS - 1

ER -

Learnability: Admissible, co-finite, and hypersimple languages

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this