東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Uncertainty Estimation Toward Safe AI.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Uncertainty Estimation Toward Safe AI./
作者:	Park, Sangdon.
面頁冊數:	1 online resource (197 pages)
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647723click for full text (PQDT)
ISBN:	9798535591179

Uncertainty Estimation Toward Safe AI.
Park, Sangdon.

Uncertainty Estimation Toward Safe AI. - 1 online resource (197 pages)

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--University of Pennsylvania, 2021.

Includes bibliographical references

Safety critical AI systems interact with environments based on inductively learned predictors, which may not be always correct. To complement the incorrect predictions, quantifying uncertainty on predictions is crucial to guarantee the safety of the AI systems. The major challenge of uncertainty quantification is making theoretical guarantees for the correctness of uncertainty estimation in various environments. In this thesis, we propose novel approaches on quantifying uncertainty possibly with correctness guarantees under two major environments: (1) the i.i.d. environment, i.e., where the distributions of learning-time and inference-time are identical, and (2) the covariate shift environment, i.e., where covariate distributions of learning-time and inference-time can be different. In particular, we propose an algorithm to construct a set predictor over labels, i.e., a prediction set, that satisfies a probably approximately correct (PAC) guarantee under the i.i.d. and covariate shift environments, while the prediction set size is small enough to be useful as an uncertainty quantifier. Here, the guarantee on the covariate shift assumes the smoothness of covariate distributions. An alternative way to represent uncertainty is via the confidence of predictors; we also propose an algorithm to estimate the confidence of classifiers that comes with the PAC guarantee under the i.i.d. environment, and we rigorously estimate the confidence under the covariate shift environment. We demonstrate that the proposed approaches are practically useful over various tasks, including image classification, visual object detection, visual object tracking, false medical alarm suppression, state estimation in reinforcement learning, fast deep neural network inference, and safe reinforcement learning.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798535591179Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Artificial intelligenceIndex Terms--Genre/Form:

542853
Electronic books.

Uncertainty Estimation Toward Safe AI.
LDR:03207nmm a2200409K 4500 001 2357219
005 20230622065019.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798535591179
035 $a (MiAaPQ)AAI28647723
035 $a AAI28647723
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Park, Sangdon. $3 3697749
245 1 0 $a Uncertainty Estimation Toward Safe AI.
264 0 $c 2021
300 $a 1 online resource (197 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: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Lee, Insup; Bastani, Osbert.
502 $a Thesis (Ph.D.)--University of Pennsylvania, 2021.
504 $a Includes bibliographical references
520 $a Safety critical AI systems interact with environments based on inductively learned predictors, which may not be always correct. To complement the incorrect predictions, quantifying uncertainty on predictions is crucial to guarantee the safety of the AI systems. The major challenge of uncertainty quantification is making theoretical guarantees for the correctness of uncertainty estimation in various environments. In this thesis, we propose novel approaches on quantifying uncertainty possibly with correctness guarantees under two major environments: (1) the i.i.d. environment, i.e., where the distributions of learning-time and inference-time are identical, and (2) the covariate shift environment, i.e., where covariate distributions of learning-time and inference-time can be different. In particular, we propose an algorithm to construct a set predictor over labels, i.e., a prediction set, that satisfies a probably approximately correct (PAC) guarantee under the i.i.d. and covariate shift environments, while the prediction set size is small enough to be useful as an uncertainty quantifier. Here, the guarantee on the covariate shift assumes the smoothness of covariate distributions. An alternative way to represent uncertainty is via the confidence of predictors; we also propose an algorithm to estimate the confidence of classifiers that comes with the PAC guarantee under the i.i.d. environment, and we rigorously estimate the confidence under the covariate shift environment. We demonstrate that the proposed approaches are practically useful over various tasks, including image classification, visual object detection, visual object tracking, false medical alarm suppression, state estimation in reinforcement learning, fast deep neural network inference, and safe reinforcement learning.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Mathematics. $3 515831
650 4 $a Artificial intelligence. $3 516317
650 4 $a Datasets. $3 3541416
650 4 $a Experiments. $3 525909
650 4 $a Calibration. $3 2068745
650 4 $a Neural networks. $3 677449
650 4 $a Classification. $3 595585
650 4 $a Boxes. $3 3564918
650 4 $a Algorithms. $3 536374
650 4 $a Ablation. $3 3562462
653 $a Artificial intelligence
653 $a Calibration
653 $a Prediction set
653 $a Probably approximately correct
653 $a Safety
653 $a Uncertainty quantification
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0800
690 $a 0405
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Pennsylvania. $b Computer and Information Science. $3 2092564
773 0 $t Dissertations Abstracts International $g 83-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647723 $z click for full text (PQDT)