Please use this identifier to cite or link to this item:
https://doi.org/10.1109/18.915700
DC Field | Value | |
---|---|---|
dc.title | The one-inclusion graph algorithm is near-optimal for the prediction model of learning | |
dc.contributor.author | Li, Y. | |
dc.contributor.author | Long, P.M. | |
dc.contributor.author | Srinivasan, A. | |
dc.date.accessioned | 2013-07-23T09:32:11Z | |
dc.date.available | 2013-07-23T09:32:11Z | |
dc.date.issued | 2001 | |
dc.identifier.citation | Li, Y., Long, P.M., Srinivasan, A. (2001). The one-inclusion graph algorithm is near-optimal for the prediction model of learning. IEEE Transactions on Information Theory 47 (3) : 1257-1261. ScholarBank@NUS Repository. https://doi.org/10.1109/18.915700 | |
dc.identifier.issn | 00189448 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/43369 | |
dc.description.abstract | Haussler, Littlestone, and Warmuth described a general-purpose algorithm for learning according to the prediction model, and proved an upper bound on the probability that their algorithm makes a mistake in terms of the number of examples seen and the Vapnik-Chervonenkis (VC) dimension of the concept class being learned. We show that their bound is within a factor of 1 + o(1) of the best possible such bound for any algorithm. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/18.915700 | |
dc.source | Scopus | |
dc.subject | Computational learning | |
dc.subject | One-inclusion graph algorithm | |
dc.subject | Prediction model | |
dc.subject | Sample complexity | |
dc.subject | Vapnik-Chervonenkis (VC) dimension | |
dc.type | Others | |
dc.contributor.department | MATERIALS SCIENCE | |
dc.contributor.department | COMPUTER SCIENCE | |
dc.description.doi | 10.1109/18.915700 | |
dc.description.sourcetitle | IEEE Transactions on Information Theory | |
dc.description.volume | 47 | |
dc.description.issue | 3 | |
dc.description.page | 1257-1261 | |
dc.description.coden | IETTA | |
dc.identifier.isiut | 000167956600040 | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.