Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0022-0000(03)00067-9
DC FieldValue
dc.titleIntrinsic complexity of learning geometrical concepts from positive data
dc.contributor.authorJain, S.
dc.contributor.authorKinber, E.
dc.date.accessioned2013-07-04T07:34:17Z
dc.date.available2013-07-04T07:34:17Z
dc.date.issued2003
dc.identifier.citationJain, S., Kinber, E. (2003). Intrinsic complexity of learning geometrical concepts from positive data. Journal of Computer and System Sciences 67 (3) : 546-607. ScholarBank@NUS Repository. https://doi.org/10.1016/S0022-0000(03)00067-9
dc.identifier.issn00220000
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39115
dc.description.abstractIntrinsic complexity is used to measure the complexity of learning areas limited by broken-straight lines (called open semi-hulls) and intersections of such areas. Any strategy learning such geometrical concepts can be viewed as a sequence of primitive basic strategies. Thus, the length of such a sequence together with the complexities of the primitive strategies used can be regarded as the complexity of learning the concepts in question. We obtained the best possible lower and upper bounds on learning open semi-hulls, as well as matching upper and lower bounds on the complexity of learning intersections of such areas. Surprisingly, upper bounds in both cases turn out to be much lower than those provided by natural learning strategies. Another surprising result is that learning intersections of open semi-hulls turns out to be easier than learning open semi-hulls themselves. © 2003 Elsevier Science (USA). All rights reserved.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/S0022-0000(03)00067-9
dc.sourceScopus
dc.typeArticle
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1016/S0022-0000(03)00067-9
dc.description.sourcetitleJournal of Computer and System Sciences
dc.description.volume67
dc.description.issue3
dc.description.page546-607
dc.description.codenJCSSB
dc.identifier.isiut000186262700003
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

3
checked on Oct 16, 2019

WEB OF SCIENCETM
Citations

3
checked on Oct 9, 2019

Page view(s)

56
checked on Oct 14, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.