Noise model on learning sets of strings

Yasubumi Sakakibara, Rani Siromoney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

In this paper, we introduce a new noise model on learning sets of strings in the framework of PAC learning and consider the effect of the noise on learning. The instance domain is the set Σn of strings over a finite alphabet Σ, and the examples are corrupted by purely random errors affecting only the instances (and not the labels). We consider three types of errors on instances, called EDIT operation errors. EDIT operations consist of `insertion', `deletion', and `change' of a symbol in a string. We call such a noise where the examples are corrupted by random errors of EDIT operations on instances the EDIT noise. First we show general upper bounds on the EDIT noise rate that a learning algorithm of taking the strategy of minimizing disagreements can tolerate and a learning algorithm can tolerate. Next we present an efficient algorithm that can learn a class of decision lists over the attributes `a string w contains a pattern p?' from noisy examples under some restriction on the EDIT noise rate.

Original languageEnglish
Title of host publicationProceedings of the Fifth Annual ACM Workshop on Computational Learning Theory
PublisherPubl by ACM
Pages295-302
Number of pages8
ISBN (Print)089791497X
Publication statusPublished - 1992
Externally publishedYes
EventProceedings of the Fifth Annual ACM Workshop on Computational Learning Theory - Pittsburgh, PA, USA
Duration: 1992 Jul 271992 Jul 29

Other

OtherProceedings of the Fifth Annual ACM Workshop on Computational Learning Theory
CityPittsburgh, PA, USA
Period92/7/2792/7/29

Fingerprint

Random errors
Learning algorithms
Labels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sakakibara, Y., & Siromoney, R. (1992). Noise model on learning sets of strings. In Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory (pp. 295-302). Publ by ACM.

Noise model on learning sets of strings. / Sakakibara, Yasubumi; Siromoney, Rani.

Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory. Publ by ACM, 1992. p. 295-302.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sakakibara, Y & Siromoney, R 1992, Noise model on learning sets of strings. in Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory. Publ by ACM, pp. 295-302, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, USA, 92/7/27.
Sakakibara Y, Siromoney R. Noise model on learning sets of strings. In Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory. Publ by ACM. 1992. p. 295-302
Sakakibara, Yasubumi ; Siromoney, Rani. / Noise model on learning sets of strings. Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory. Publ by ACM, 1992. pp. 295-302
@inproceedings{81d4a333dec042a280440fa476a0800e,
title = "Noise model on learning sets of strings",
abstract = "In this paper, we introduce a new noise model on learning sets of strings in the framework of PAC learning and consider the effect of the noise on learning. The instance domain is the set Σn of strings over a finite alphabet Σ, and the examples are corrupted by purely random errors affecting only the instances (and not the labels). We consider three types of errors on instances, called EDIT operation errors. EDIT operations consist of `insertion', `deletion', and `change' of a symbol in a string. We call such a noise where the examples are corrupted by random errors of EDIT operations on instances the EDIT noise. First we show general upper bounds on the EDIT noise rate that a learning algorithm of taking the strategy of minimizing disagreements can tolerate and a learning algorithm can tolerate. Next we present an efficient algorithm that can learn a class of decision lists over the attributes `a string w contains a pattern p?' from noisy examples under some restriction on the EDIT noise rate.",
author = "Yasubumi Sakakibara and Rani Siromoney",
year = "1992",
language = "English",
isbn = "089791497X",
pages = "295--302",
booktitle = "Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory",
publisher = "Publ by ACM",

}

TY - GEN

T1 - Noise model on learning sets of strings

AU - Sakakibara, Yasubumi

AU - Siromoney, Rani

PY - 1992

Y1 - 1992

N2 - In this paper, we introduce a new noise model on learning sets of strings in the framework of PAC learning and consider the effect of the noise on learning. The instance domain is the set Σn of strings over a finite alphabet Σ, and the examples are corrupted by purely random errors affecting only the instances (and not the labels). We consider three types of errors on instances, called EDIT operation errors. EDIT operations consist of `insertion', `deletion', and `change' of a symbol in a string. We call such a noise where the examples are corrupted by random errors of EDIT operations on instances the EDIT noise. First we show general upper bounds on the EDIT noise rate that a learning algorithm of taking the strategy of minimizing disagreements can tolerate and a learning algorithm can tolerate. Next we present an efficient algorithm that can learn a class of decision lists over the attributes `a string w contains a pattern p?' from noisy examples under some restriction on the EDIT noise rate.

AB - In this paper, we introduce a new noise model on learning sets of strings in the framework of PAC learning and consider the effect of the noise on learning. The instance domain is the set Σn of strings over a finite alphabet Σ, and the examples are corrupted by purely random errors affecting only the instances (and not the labels). We consider three types of errors on instances, called EDIT operation errors. EDIT operations consist of `insertion', `deletion', and `change' of a symbol in a string. We call such a noise where the examples are corrupted by random errors of EDIT operations on instances the EDIT noise. First we show general upper bounds on the EDIT noise rate that a learning algorithm of taking the strategy of minimizing disagreements can tolerate and a learning algorithm can tolerate. Next we present an efficient algorithm that can learn a class of decision lists over the attributes `a string w contains a pattern p?' from noisy examples under some restriction on the EDIT noise rate.

UR - http://www.scopus.com/inward/record.url?scp=0026987081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026987081&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026987081

SN - 089791497X

SP - 295

EP - 302

BT - Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory

PB - Publ by ACM

ER -