國立虎尾科技大學 |

Where Are the Humans in Human-AI Interaction : = The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Where Are the Humans in Human-AI Interaction :/
其他題名:	The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning.
作者:	Kaur, Harmanpreet.
面頁冊數:	1 online resource (202 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798380371452

Where Are the Humans in Human-AI Interaction : = The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning.
Kaur, Harmanpreet.

Where Are the Humans in Human-AI Interaction :The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning. - 1 online resource (202 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--University of Michigan, 2023.

Includes bibliographical references

This dissertation aims to provide a richer understanding of the extent to which people understand complex AI and ML outputs and reasoning, what influences their understanding, and how we can continue to enhance it going forward. AI- and ML-based systems are now routinely deployed in real-world settings, including sensitive domains like criminal justice, healthcare, finance, and public policy. Given their rapidly growing ubiquity, understanding how AI and ML work is a prerequisite for responsibly designing, deploying, and using these systems. With interpretability and explainability approaches, these systems can offer explanations for their outputs to aid human understanding. Though these approaches rely on guidelines for how humans explain things to each other, they ultimately solve for improving an artifact (e.g., an explanation or explanation system). My dissertation makes the argument that helping people understand AI and ML is as much a human problem as a technical one. Detailing this vital human-centered piece, I present work that shows that current interpretability and explainability tools do not meet their intended goals for a key stakeholder, ML practitioners, who end up either over- or under-utilizing these tools. Investigating the reasons behind this behavior, I apply the cognitive model of bounded rationality to the human-machine setting. Under this model of decision-making, people select plausible options based on their prior heuristics rather than internalizing all relevant information. I find significant evidence showing that interpretability tools exacerbate the application of bounded rationality. As a solution, I present a new framework for re-imagining interpretability and explainability based on sensemaking theory from organizational studies. This Sensible AI framework prescribes design guidelines grounded in nuances of human cognition-facets of the individual and their environmental, social, and organizational context.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380371452Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

554714
Electronic books.

Where Are the Humans in Human-AI Interaction : = The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning.
LDR:03460ntm a22004097 4500 001 1145337
005 20240618081822.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380371452
035 $a (MiAaPQ)AAI30747542
035 $a (MiAaPQ)umichrackham005035
035 $a AAI30747542
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kaur, Harmanpreet. $3 1470632
245 1 0 $a Where Are the Humans in Human-AI Interaction : $b The Missing Human-Centered Perspective on Interpretability Tools for Machine Learning.
264 0 $c 2023
300 $a 1 online resource (202 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: 85-03, Section: B.
500 $a Advisor: Gilbert, Eric; Lampe, Cliff.
502 $a Thesis (Ph.D.)--University of Michigan, 2023.
504 $a Includes bibliographical references
520 $a This dissertation aims to provide a richer understanding of the extent to which people understand complex AI and ML outputs and reasoning, what influences their understanding, and how we can continue to enhance it going forward. AI- and ML-based systems are now routinely deployed in real-world settings, including sensitive domains like criminal justice, healthcare, finance, and public policy. Given their rapidly growing ubiquity, understanding how AI and ML work is a prerequisite for responsibly designing, deploying, and using these systems. With interpretability and explainability approaches, these systems can offer explanations for their outputs to aid human understanding. Though these approaches rely on guidelines for how humans explain things to each other, they ultimately solve for improving an artifact (e.g., an explanation or explanation system). My dissertation makes the argument that helping people understand AI and ML is as much a human problem as a technical one. Detailing this vital human-centered piece, I present work that shows that current interpretability and explainability tools do not meet their intended goals for a key stakeholder, ML practitioners, who end up either over- or under-utilizing these tools. Investigating the reasons behind this behavior, I apply the cognitive model of bounded rationality to the human-machine setting. Under this model of decision-making, people select plausible options based on their prior heuristics rather than internalizing all relevant information. I find significant evidence showing that interpretability tools exacerbate the application of bounded rationality. As a solution, I present a new framework for re-imagining interpretability and explainability based on sensemaking theory from organizational studies. This Sensible AI framework prescribes design guidelines grounded in nuances of human cognition-facets of the individual and their environmental, social, and organizational context.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Information science. $3 561178
653 $a Machine learning
653 $a Explainability tools
653 $a Sensemaking
653 $a Bounded rationality
653 $a Human cognition
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Michigan. $b Info & Comp Sci & Engin PhD. $3 1470633
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30747542 $z click for full text (PQDT)