On learning from queries and counterexamples in the presence of noise

Yasubumi Sakakibara

doi:10.1016/0020-0190(91)90220-C

On learning from queries and counterexamples in the presence of noise

Yasubumi Sakakibara

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

6 Citations (Scopus)

Abstract

Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.

Original language	English
Pages (from-to)	279-284
Number of pages	6
Journal	Information Processing Letters
Volume	37
Issue number	5
DOIs	https://doi.org/10.1016/0020-0190(91)90220-C
Publication status	Published - 1991 Mar 14
Externally published	Yes

Keywords

Concept learning
analysis of algorithms
formal languages
noise
queries
random sampling

ASJC Scopus subject areas

Theoretical Computer Science
Signal Processing
Information Systems
Computer Science Applications

Access to Document

10.1016/0020-0190(91)90220-C

Cite this

@article{7a90c5b3b24d4875b791dda650e317c1,

title = "On learning from queries and counterexamples in the presence of noise",

abstract = "Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.",

keywords = "Concept learning, analysis of algorithms, formal languages, noise, queries, random sampling",

author = "Yasubumi Sakakibara",

year = "1991",

month = mar,

day = "14",

doi = "10.1016/0020-0190(91)90220-C",

language = "English",

volume = "37",

pages = "279--284",

journal = "Information Processing Letters",

issn = "0020-0190",

publisher = "Elsevier",

number = "5",

}

TY - JOUR

T1 - On learning from queries and counterexamples in the presence of noise

AU - Sakakibara, Yasubumi

PY - 1991/3/14

Y1 - 1991/3/14

N2 - Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.

AB - Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.

KW - Concept learning

KW - analysis of algorithms

KW - formal languages

KW - noise

KW - queries

KW - random sampling

UR - http://www.scopus.com/inward/record.url?scp=0026119624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026119624&partnerID=8YFLogxK

U2 - 10.1016/0020-0190(91)90220-C

DO - 10.1016/0020-0190(91)90220-C

M3 - Article

AN - SCOPUS:0026119624

SN - 0020-0190

VL - 37

SP - 279

EP - 284

JO - Information Processing Letters

JF - Information Processing Letters

IS - 5

ER -

On learning from queries and counterexamples in the presence of noise

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this