國立虎尾科技大學 |

Estimating Confidences for Classifier Decisions using Extreme Value Theory.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Estimating Confidences for Classifier Decisions using Extreme Value Theory./
作者:	Fragoso, Victor M.
面頁冊數:	1 online resource (133 pages)
附註:	Source: Dissertation Abstracts International, Volume: 76-07(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781321567762

Estimating Confidences for Classifier Decisions using Extreme Value Theory.
Fragoso, Victor M.

Estimating Confidences for Classifier Decisions using Extreme Value Theory. - 1 online resource (133 pages)

Source: Dissertation Abstracts International, Volume: 76-07(E), Section: B.

Thesis (Ph.D.)--University of California, Santa Barbara, 2014.

Includes bibliographical references

Classifiers generally lack a mechanism to compute decision confidences. As humans, when we sense that the confidence for a decision is low, we either conduct additional actions to improve our confidence or dismiss the decision. While this reasoning is natural to us, it is currently missing in most common decision algorithms (i.e., classifiers) used in computer vision or machine learning. This limits the capability for a machine to take further actions to either improve a result or dismiss the decision. In this thesis, we design algorithms for estimating the confidence for decisions made by classifiers such as nearest-neighbor or support vector machines. We developed these algorithms leveraging the theory of extreme values. We use the statistical models that this theory provides for modeling the classifier's decision scores for correct and incorrect outcomes. Our proposed algorithms exploit these statistical models in order to compute a correctness belief: the probability that the classifier's decision is correct. In this work, we show how these beliefs can be used to filter bad classifications and to speed up robust estimations via sample and consensus algorithms, which are used in computer vision for estimating camera motions and for reconstructing the scene's 3D structure. Moreover, we show how these beliefs improve the classification accuracy of one-class support vector machines. In conclusion, we show that extreme value theory leads to powerful mechanisms that can predict the correctness of a classifier's decision.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781321567762Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Estimating Confidences for Classifier Decisions using Extreme Value Theory.
LDR:02694ntm a2200313K 4500 001 913763
005 20180622095237.5
006 m o u
007 cr mn||||a|a||
008 190606s2014 xx obm 000 0 eng d
020 $a 9781321567762
035 $a (MiAaPQ)AAI3682901
035 $a (MiAaPQ)ucsb:12441
035 $a AAI3682901
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Fragoso, Victor M. $3 1186731
245 1 0 $a Estimating Confidences for Classifier Decisions using Extreme Value Theory.
264 0 $c 2014
300 $a 1 online resource (133 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 76-07(E), Section: B.
500 $a Adviser: Matthew A. Turk.
502 $a Thesis (Ph.D.)--University of California, Santa Barbara, 2014.
504 $a Includes bibliographical references
520 $a Classifiers generally lack a mechanism to compute decision confidences. As humans, when we sense that the confidence for a decision is low, we either conduct additional actions to improve our confidence or dismiss the decision. While this reasoning is natural to us, it is currently missing in most common decision algorithms (i.e., classifiers) used in computer vision or machine learning. This limits the capability for a machine to take further actions to either improve a result or dismiss the decision. In this thesis, we design algorithms for estimating the confidence for decisions made by classifiers such as nearest-neighbor or support vector machines. We developed these algorithms leveraging the theory of extreme values. We use the statistical models that this theory provides for modeling the classifier's decision scores for correct and incorrect outcomes. Our proposed algorithms exploit these statistical models in order to compute a correctness belief: the probability that the classifier's decision is correct. In this work, we show how these beliefs can be used to filter bad classifications and to speed up robust estimations via sample and consensus algorithms, which are used in computer vision for estimating camera motions and for reconstructing the scene's 3D structure. Moreover, we show how these beliefs improve the classification accuracy of one-class support vector machines. In conclusion, we show that extreme value theory leads to powerful mechanisms that can predict the correctness of a classifier's decision.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Santa Barbara. $b Computer Science. $3 1182528
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3682901 $z click for full text (PQDT)