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

Understanding Biomedical Machine Learning Models.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Understanding Biomedical Machine Learning Models./
作者:	Janizek, Joseph D.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	229 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
Contained By:	Dissertations Abstracts International83-10B.
標題:	Computer science. -
ISBN:	9798426801394

Understanding Biomedical Machine Learning Models.
Janizek, Joseph D.

Understanding Biomedical Machine Learning Models. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 229 p.

Source: Dissertations Abstracts International, Volume: 83-10, Section: B.

Thesis (Ph.D.)--University of Washington, 2022.

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

As complex, black box models have increasingly come to predominate the algorithms used in state-of-the-art machine learning pipelines, the need to explain and understand the predictions made by these algorithms has grown correspondingly. Feature attribution methods are one popular approach to explain these black box models, but are limited in their expressive capacity. We therefore propose three approaches to go beyond the shortcomings of existing feature attribution methods. The first, EXPRESS, demonstrates how the stability and quality of feature attributions for models of gene expression data increase when these models are ensembled. The second, Integrated Hessians, efficiently explains the interactions between pairs of features for neural network models, which we show has general applications even beyond biological and medical models. In a third approach, we apply generative adversarial networks and saliency maps to identify the underlying reasons for poor generalizability of radiographic COVID-19 detection models. Furthermore, while the utility of feature attribution methods for helping humans understand what models have learned is well-known, their utility for helping humans express their own desiderata in machine-interpretable language is under-appreciated. We develop a feature attribution method that is designed for use during model training, and demonstrate how it can be used to incorporate gene interaction networks as a constraint on predictive models with gene expression features. Finally, we show how to enforce more abstract model constraints using adversarial training in the context of radiographic pneumonia classification.

ISBN: 9798426801394Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

AI

Understanding Biomedical Machine Learning Models.
LDR:02752nmm a2200385 4500 001 2349704
005 20221003074934.5
008 241004s2022 eng d
020 $a 9798426801394
035 $a (MiAaPQ)AAI29060914
035 $a AAI29060914
040 $a MiAaPQ $c MiAaPQ
100 1 $a Janizek, Joseph D. $3 3689119
245 1 0 $a Understanding Biomedical Machine Learning Models.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 229 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
500 $a Advisor: Lee, Su-In.
502 $a Thesis (Ph.D.)--University of Washington, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a As complex, black box models have increasingly come to predominate the algorithms used in state-of-the-art machine learning pipelines, the need to explain and understand the predictions made by these algorithms has grown correspondingly. Feature attribution methods are one popular approach to explain these black box models, but are limited in their expressive capacity. We therefore propose three approaches to go beyond the shortcomings of existing feature attribution methods. The first, EXPRESS, demonstrates how the stability and quality of feature attributions for models of gene expression data increase when these models are ensembled. The second, Integrated Hessians, efficiently explains the interactions between pairs of features for neural network models, which we show has general applications even beyond biological and medical models. In a third approach, we apply generative adversarial networks and saliency maps to identify the underlying reasons for poor generalizability of radiographic COVID-19 detection models. Furthermore, while the utility of feature attribution methods for helping humans understand what models have learned is well-known, their utility for helping humans express their own desiderata in machine-interpretable language is under-appreciated. We develop a feature attribution method that is designed for use during model training, and demonstrate how it can be used to incorporate gene interaction networks as a constraint on predictive models with gene expression features. Finally, we show how to enforce more abstract model constraints using adversarial training in the context of radiographic pneumonia classification.
590 $a School code: 0250.
650 4 $a Computer science. $3 523869
650 4 $a Biomedical engineering. $3 535387
650 4 $a Medical imaging. $3 3172799
650 4 $a Artificial intelligence. $3 516317
653 $a AI
653 $a Biomedicine
653 $a Computational biology
653 $a Explainable AI
653 $a Interpretability
653 $a Machine learning
690 $a 0984
690 $a 0541
690 $a 0574
690 $a 0800
710 2 0 $a University of Washington. $b Computer Science and Engineering. $3 2097608
773 0 $t Dissertations Abstracts International $g 83-10B.
790 $a 0250
791 $a Ph.D.
792 $a 2022
793 $a English