Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0022-0000(03)00067-9
Title: Intrinsic complexity of learning geometrical concepts from positive data
Authors: Jain, S. 
Kinber, E.
Issue Date: 2003
Source: Jain, 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
Abstract: Intrinsic 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.
Source Title: Journal of Computer and System Sciences
URI: http://scholarbank.nus.edu.sg/handle/10635/39115
ISSN: 00220000
DOI: 10.1016/S0022-0000(03)00067-9
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

1
checked on Dec 13, 2017

WEB OF SCIENCETM
Citations

1
checked on Nov 2, 2017

Page view(s)

46
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


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