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

Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis./
作者:	Mehta, Ronak.
面頁冊數:	1 online resource (214 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
標題:	Medical imaging. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30318783click for full text (PQDT)
ISBN:	9798379546557

Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis.
Mehta, Ronak.

Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis. - 1 online resource (214 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2023.

Includes bibliographical references

Modern machine learning has proven to be extremely effective in aiding and automating a large number of tasks, beginning with simple image recognition, now ranging widely from full language translation and understanding to computer-aided medical diagnosis and drug discovery. These advances have largely been enabled by significant development in computation schemes and algorithms, that have come alongside exponential increases in the scale of training data available. Success in these cases is measured directly by performance, evaluating some sort of error or accuracy that proves to be competitive with even domain-level experts. Recent research within the field has thus now moved to orthogonal, but equally important questions involving robustness to data distribution shifts, model fairness, interpretability of model outputs, and explainability of model predictions. The analysis of these varied questions typically look at the learning formulation with a finer toothed comb, identifying individual elements or groups of elements of interest. These ideas all fall under a similar fundamental problem of finding subsets, where they be of groups within the population, features of the input, or sections of the model. Uniquely shaped by their particular machine learning instantiations, we need methods for identifying (1) subsets of training samples or subpopulations which have disparate outcomes for a given model, (2) feature subsets that are sufficient or uniquely explain a particular model prediction, and (3) important parameter subsets or paths through neural network models that explicitly describe how a model output was generated. In this dissertation, we will describe a number of methods for addressing these subset selection problems. Developing mathematical tools based primarily on aspects of differential geometry and conditional independence, we will demonstrate theoretical and empirical effectiveness of these methods on a wide breadth of problems that can be distilled in the manner above, including hypothesis testing with medical imaging, predicting disease progression, machine unlearning, and increasing model fairness.

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

Mode of access: World Wide Web

ISBN: 9798379546557Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Conditional independenceIndex Terms--Genre/Form:

542853
Electronic books.

Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis.
LDR:03569nmm a2200397K 4500 001 2358392
005 20230731112638.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379546557
035 $a (MiAaPQ)AAI30318783
035 $a AAI30318783
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Mehta, Ronak. $3 3698923
245 1 0 $a Identifying Feature, Parameter, and Sample Subsets in Machine Learning and Image Analysis.
264 0 $c 2023
300 $a 1 online resource (214 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: 84-11, Section: B.
500 $a Advisor: Singh, Vikas.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2023.
504 $a Includes bibliographical references
520 $a Modern machine learning has proven to be extremely effective in aiding and automating a large number of tasks, beginning with simple image recognition, now ranging widely from full language translation and understanding to computer-aided medical diagnosis and drug discovery. These advances have largely been enabled by significant development in computation schemes and algorithms, that have come alongside exponential increases in the scale of training data available. Success in these cases is measured directly by performance, evaluating some sort of error or accuracy that proves to be competitive with even domain-level experts. Recent research within the field has thus now moved to orthogonal, but equally important questions involving robustness to data distribution shifts, model fairness, interpretability of model outputs, and explainability of model predictions. The analysis of these varied questions typically look at the learning formulation with a finer toothed comb, identifying individual elements or groups of elements of interest. These ideas all fall under a similar fundamental problem of finding subsets, where they be of groups within the population, features of the input, or sections of the model. Uniquely shaped by their particular machine learning instantiations, we need methods for identifying (1) subsets of training samples or subpopulations which have disparate outcomes for a given model, (2) feature subsets that are sufficient or uniquely explain a particular model prediction, and (3) important parameter subsets or paths through neural network models that explicitly describe how a model output was generated. In this dissertation, we will describe a number of methods for addressing these subset selection problems. Developing mathematical tools based primarily on aspects of differential geometry and conditional independence, we will demonstrate theoretical and empirical effectiveness of these methods on a wide breadth of problems that can be distilled in the manner above, including hypothesis testing with medical imaging, predicting disease progression, machine unlearning, and increasing model fairness.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Medical imaging. $3 3172799
650 4 $a Computer science. $3 523869
653 $a Conditional independence
653 $a Differential geometry
653 $a Machine unlearning
653 $a Optimal transport
653 $a Subset selection
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0574
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The University of Wisconsin - Madison. $b Computer Sciences. $3 2099760
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30318783 $z click for full text (PQDT)