TY - JOUR
T1 - On case-based learnability of languages
AU - Globig, Christoph
AU - Jantke, Klaus P.
AU - Lange, Steffen
AU - Sakakibara, Yasubumi
N1 - Funding Information:
The work of the first three authors has been partially supported by the DEUTSCHE FORSCHUNGSGEMEINSCHAFT (DFG) within the project IND~ Our students Udo Burghardt, Volker D6tsch, and Stephan Frind at Leipzig University of Technology have developed and implemented an experimental system TIC for investigations and comparisons of several classical inductive and case-based learning algorithms. Among others, the system provides a very helpful environment for studying phenomena of learning containment decision lists. It is worth to be mentioned that the origin of the present investigations has been at the FUJITSU Laboratories in Numazu, Japan, where the last three authors had several opportunities to collaborate. We gratefully acknowledge the reports of two anonymous referees. The critical hints and the constructive suggestions helped very much to improve the presentation of our ideas and results.
PY - 1997
Y1 - 1997
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.
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 -