語系:
繁體中文
English
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
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare.
紀錄類型:
書目-電子資源 : Monograph/item
正題名/作者:
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare./
作者:
Garbin, Christian.
出版者:
Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:
115 p.
附註:
Source: Masters Abstracts International, Volume: 82-10.
Contained By:
Masters Abstracts International82-10.
標題:
Artificial intelligence. -
電子資源:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28153956
ISBN:
9798557001830
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare.
Garbin, Christian.
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare.
- Ann Arbor : ProQuest Dissertations & Theses, 2020 - 115 p.
Source: Masters Abstracts International, Volume: 82-10.
Thesis (M.S.)--Florida Atlantic University, 2020.
This item must not be sold to any third party vendors.
Artificial intelligence (AI) had a few false starts - the AI winters of the 1970s and 1980s. We are now in what looks like an AI summer. There are many useful applications of AI in the field. But there are still unfulfilled promises and outright failures. From self-driving cars that work only in constrained cases, to medical image analysis products that would replace radiologists but never did, we still struggle to translate successful research into successful real-world applications.The software engineering community has accumulated a large body of knowledge over the decades on how to develop, release, and maintain products. AI products, being software products, benefit from some of that accumulated knowledge, but not all of it. AI products diverge from traditional software products in fundamental ways: their main component is not a specific piece of code, written for a specific purpose, but a generic piece of code, a model, customized by a training process driven by hyperparameters and a dataset. Datasets are usually large and models are opaque. We cannot directly inspect them as we can inspect the code of traditional software products. We need other methods to detect failures in AI products.This thesis investigates recent advancements that promote auditing, supported by transparency, as a mechanism to detect potential failures in AI products, focusing on healthcare applications. It reviews practices that apply to the early stages of the machine learning (ML) lifecycle, when datasets and models are created. These stages are unique to AI products.The proposed solution uses checklists to increase the transparency of these early stages. The thesis investigates checklists and guidelines that have been recently proposed in the AI industry and research communities, focusing on medical applications. Out of those checklists, it selected datasheets for dataset and model cards to increase the transparency of the dataset and model creation, respectively.As a demonstration of the increased transparency afforded by these methods, this thesis applies the selected checklists to a well-known medical imaging dataset, ChestX-ray8, and to a well-known model, CheXNet. The dataset datasheet created for ChestX-ray8 and the model card created for CheXNet show how a well-structured format increases transparency. The increased transparency, in turn, allows the ML community to interact with other stakeholders, e.g. domain experts in medical imaging, early on to find potential problems and opportunities for improvement.
ISBN: 9798557001830Subjects--Topical Terms:
516317
Artificial intelligence.
Subjects--Index Terms:
Audit
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare.
LDR
:03907nmm a2200445 4500
001
2344601
005
20220531064604.5
008
241004s2020 ||||||||||||||||| ||eng d
020
$a
9798557001830
035
$a
(MiAaPQ)AAI28153956
035
$a
AAI28153956
040
$a
MiAaPQ
$c
MiAaPQ
100
1
$a
Garbin, Christian.
$3
3683386
245
1 0
$a
Assessing Methods and Tools to Improve Reporting, Increase Transparency, and Reduce Failures in Machine Learning Applications in Healthcare.
260
1
$a
Ann Arbor :
$b
ProQuest Dissertations & Theses,
$c
2020
300
$a
115 p.
500
$a
Source: Masters Abstracts International, Volume: 82-10.
500
$a
Advisor: Marques, Oge.
502
$a
Thesis (M.S.)--Florida Atlantic University, 2020.
506
$a
This item must not be sold to any third party vendors.
520
$a
Artificial intelligence (AI) had a few false starts - the AI winters of the 1970s and 1980s. We are now in what looks like an AI summer. There are many useful applications of AI in the field. But there are still unfulfilled promises and outright failures. From self-driving cars that work only in constrained cases, to medical image analysis products that would replace radiologists but never did, we still struggle to translate successful research into successful real-world applications.The software engineering community has accumulated a large body of knowledge over the decades on how to develop, release, and maintain products. AI products, being software products, benefit from some of that accumulated knowledge, but not all of it. AI products diverge from traditional software products in fundamental ways: their main component is not a specific piece of code, written for a specific purpose, but a generic piece of code, a model, customized by a training process driven by hyperparameters and a dataset. Datasets are usually large and models are opaque. We cannot directly inspect them as we can inspect the code of traditional software products. We need other methods to detect failures in AI products.This thesis investigates recent advancements that promote auditing, supported by transparency, as a mechanism to detect potential failures in AI products, focusing on healthcare applications. It reviews practices that apply to the early stages of the machine learning (ML) lifecycle, when datasets and models are created. These stages are unique to AI products.The proposed solution uses checklists to increase the transparency of these early stages. The thesis investigates checklists and guidelines that have been recently proposed in the AI industry and research communities, focusing on medical applications. Out of those checklists, it selected datasheets for dataset and model cards to increase the transparency of the dataset and model creation, respectively.As a demonstration of the increased transparency afforded by these methods, this thesis applies the selected checklists to a well-known medical imaging dataset, ChestX-ray8, and to a well-known model, CheXNet. The dataset datasheet created for ChestX-ray8 and the model card created for CheXNet show how a well-structured format increases transparency. The increased transparency, in turn, allows the ML community to interact with other stakeholders, e.g. domain experts in medical imaging, early on to find potential problems and opportunities for improvement.
590
$a
School code: 0119.
650
4
$a
Artificial intelligence.
$3
516317
650
4
$a
Computer science.
$3
523869
650
4
$a
Computer engineering.
$3
621879
650
4
$a
Medical imaging.
$3
3172799
650
4
$a
Information technology.
$3
532993
650
4
$a
Health care management.
$3
2122906
653
$a
Audit
653
$a
Machine learning
653
$a
AI applications
653
$a
Software engineering
653
$a
Traditional software products
653
$a
Coding
653
$a
Software products
653
$a
Healthcare applications
690
$a
0800
690
$a
0984
690
$a
0489
690
$a
0464
690
$a
0574
690
$a
0769
710
2
$a
Florida Atlantic University.
$b
Computer Science.
$3
3184790
773
0
$t
Masters Abstracts International
$g
82-10.
790
$a
0119
791
$a
M.S.
792
$a
2020
793
$a
English
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28153956
筆 0 讀者評論
館藏地:
全部
電子資源
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約狀態
備註欄
附件
W9467039
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
Export
取書館
處理中
...
變更密碼
登入