A noise model on learning sets of strings

Authors:
Yasubumi Sakakibara;Rani Siromoney
Affiliations:
International Institute for Advanced Study of Social Information Science (IIAS-SIS), Fujitsu Laboratories Ltd., 140, Miyamoto, Numazu, Shizuoka 410-03, Japan;Madras Christian College, Tambaram, Madras 600 059, India
Venue:
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Year:
1992

Citing 7
Cited 4

A theory of the learnable

Communications of the ACM
Algorithms for approximate string matching

Information and Control
Fast string matching with k-differences

Journal of Computer and System Sciences - 26th IEEE Conference on Foundations of Computer Science, October 21-23, 1985
Learning in the presence of malicious errors

STOC '88 Proceedings of the twentieth annual ACM symposium on Theory of computing
Types of noise in data for concept learning

COLT '88 Proceedings of the first annual workshop on Computational learning theory
Learning Decision Lists

Machine Learning
Learning From Noisy Examples

Machine Learning

Learning fallible finite state automata

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Refutable/Inductive Learning from Neighbor Examples and Its Application to Decision Trees over Patterns

Progress in Discovery Science, Final Report of the Japanese Discovery Science Project
Decision lists over regular patterns

Theoretical Computer Science - Selected papers in honour of Setsuo Arikawa
Learning stochastic edit distance: Application in handwritten character recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

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 &Sgr;n of strings over a finite alphabet &Sgr;, 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.