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

Model Interpretation and Data Valuation for Machine Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Model Interpretation and Data Valuation for Machine Learning./
作者:	Ghorbani, Amirata.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	207 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Neurons. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28671242
ISBN:	9798544201106

Model Interpretation and Data Valuation for Machine Learning.
Ghorbani, Amirata.

Model Interpretation and Data Valuation for Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 207 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

This item must not be sold to any third party vendors.

Machine learning is being applied in various critical applications like healthcare. In order to be able to trust a machine learning model and to repair it once it malfunctions, it is important to be able to interpret its decision-making. For example, if a model's performance is poor on a specific subgroup (gender, race, etc), it is important to find out why and fix it. In this thesis, we examine the drawbacks of existing interpretability methods and introduce new ML interpretability algorithms that are designed to tackle some of the shortcomings.Data is the labor that trains machine learning models. It is not possible to interpret an ML model's behavior without going back to the data that trained it in the first place. A fundamental challenge is how to quantify the contribution of each source of data to the model's performance. For example, in healthcare and consumer markets, it has been suggested that individuals should be compensated for the data that they generate, but it is not clear what is an equitable valuation for individual datum. In this thesis, we discuss principled frameworks for equitable valuation of data; that is, given a learning algorithm and a performance metric that quantifies the performance of the resulting model, we try to find the contribution of individual datum.This thesis is divided in 3 sections, machine learning interpretability and fairness, data valuation, and machine learning for healthcare - all linked by the common goal of making the use of machine learning more responsible for the benefit of human beings.

ISBN: 9798544201106Subjects--Topical Terms:

588699
Neurons.

Model Interpretation and Data Valuation for Machine Learning.
LDR:02594nmm a2200313 4500 001 2349834
005 20221010063634.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798544201106
035 $a (MiAaPQ)AAI28671242
035 $a (MiAaPQ)STANFORDdj449dg7488
035 $a AAI28671242
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ghorbani, Amirata. $3 3689254
245 1 0 $a Model Interpretation and Data Valuation for Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 207 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Zou, James Y.;Pauly, John;Weissman, Tsachy.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Machine learning is being applied in various critical applications like healthcare. In order to be able to trust a machine learning model and to repair it once it malfunctions, it is important to be able to interpret its decision-making. For example, if a model's performance is poor on a specific subgroup (gender, race, etc), it is important to find out why and fix it. In this thesis, we examine the drawbacks of existing interpretability methods and introduce new ML interpretability algorithms that are designed to tackle some of the shortcomings.Data is the labor that trains machine learning models. It is not possible to interpret an ML model's behavior without going back to the data that trained it in the first place. A fundamental challenge is how to quantify the contribution of each source of data to the model's performance. For example, in healthcare and consumer markets, it has been suggested that individuals should be compensated for the data that they generate, but it is not clear what is an equitable valuation for individual datum. In this thesis, we discuss principled frameworks for equitable valuation of data; that is, given a learning algorithm and a performance metric that quantifies the performance of the resulting model, we try to find the contribution of individual datum.This thesis is divided in 3 sections, machine learning interpretability and fairness, data valuation, and machine learning for healthcare - all linked by the common goal of making the use of machine learning more responsible for the benefit of human beings.
590 $a School code: 0212.
650 4 $a Neurons. $3 588699
650 4 $a Neural networks. $3 677449
650 4 $a Maps. $3 544078
650 4 $a Algorithms. $3 536374
650 4 $a Human subjects. $3 3562959
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
690 $a 0800
690 $a 0984
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-05B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28671242