On case-based learnability of languages

Christoph Globig, Klaus P. Jantke, Steffen Lange, Yasubumi Sakakibara

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations. Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.

Original languageEnglish
Pages (from-to)59-83
Number of pages25
JournalNew Generation Computing
Volume15
Issue number1
DOIs
Publication statusPublished - 1997 Mar
Externally publishedYes

Fingerprint

Learnability
Case based reasoning
Case-based Reasoning
Formal languages
Formal Languages
Similarity Measure
Knowledge acquisition
Representability
Artificial intelligence
Knowledge Acquisition
Life cycle
Life Cycle
Immediately
Artificial Intelligence
Paradigm
Processing
Language
Learning
Class
Form

Keywords

  • Case-based Learning
  • Containment Decision Lists
  • Formal Language Learning
  • Inductive Inference
  • Instance-based Learning

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Hardware and Architecture
  • Computer Networks and Communications
  • Computational Theory and Mathematics

Cite this

On case-based learnability of languages. / Globig, Christoph; Jantke, Klaus P.; Lange, Steffen; Sakakibara, Yasubumi.

In: New Generation Computing, Vol. 15, No. 1, 03.1997, p. 59-83.

Research output: Contribution to journalArticle

Globig, Christoph ; Jantke, Klaus P. ; Lange, Steffen ; Sakakibara, Yasubumi. / On case-based learnability of languages. In: New Generation Computing. 1997 ; Vol. 15, No. 1. pp. 59-83.
@article{e5cdd316a4a344e2a741ffc1c5332695,
title = "On case-based learnability of languages",
abstract = "Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations. Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.",
keywords = "Case-based Learning, Containment Decision Lists, Formal Language Learning, Inductive Inference, Instance-based Learning",
author = "Christoph Globig and Jantke, {Klaus P.} and Steffen Lange and Yasubumi Sakakibara",
year = "1997",
month = "3",
doi = "10.1007/BF03037560",
language = "English",
volume = "15",
pages = "59--83",
journal = "New Generation Computing",
issn = "0288-3635",
publisher = "Springer Japan",
number = "1",

}

TY - JOUR

T1 - On case-based learnability of languages

AU - Globig, Christoph

AU - Jantke, Klaus P.

AU - Lange, Steffen

AU - Sakakibara, Yasubumi

PY - 1997/3

Y1 - 1997/3

N2 - Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations. Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.

AB - Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations. Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.

KW - Case-based Learning

KW - Containment Decision Lists

KW - Formal Language Learning

KW - Inductive Inference

KW - Instance-based Learning

UR - http://www.scopus.com/inward/record.url?scp=0030736295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030736295&partnerID=8YFLogxK

U2 - 10.1007/BF03037560

DO - 10.1007/BF03037560

M3 - Article

AN - SCOPUS:0030736295

VL - 15

SP - 59

EP - 83

JO - New Generation Computing

JF - New Generation Computing

SN - 0288-3635

IS - 1

ER -