國立虎尾科技大學 |

Explainable AI for Human and Science.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Explainable AI for Human and Science./
作者:	Tan, Juntao.
面頁冊數:	1 online resource (136 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-08, Section: B.
Contained By:	Dissertations Abstracts International85-08B.
標題:	Computer engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798381741612

Explainable AI for Human and Science.
Tan, Juntao.

Explainable AI for Human and Science. - 1 online resource (136 pages)

Source: Dissertations Abstracts International, Volume: 85-08, Section: B.

Thesis (Ph.D.)--Rutgers The State University of New Jersey, School of Graduate Studies, 2024.

Includes bibliographical references

Artificial Intelligence (AI) goes beyond merely making predictions. Its explainability is crucial not only for enhancing user satisfaction but also for facilitating more effective decision-making. Given the remarkable advancements in AI models and their critical roles in both human-centered applications and scientific research in recent years, the demand for explainable AI has never been greater.Among all available methods for achieving explainable AI, this dissertation focuses on the specialized domain of counterfactual explanations. Counterfactual explanations offer a unique interpretation of systems by providing "what-if" scenarios that illuminate how a given outcome could differ if the system input were altered. The model-agnostic nature of counterfactual explanations makes them exceptionally well-suited for elucidating the intrinsic mechanisms of advanced AI systems. This is particularly critical in an era where such systems, especially those employing deep neural networks, are becoming increasingly opaque and complex.An in-depth investigation is conducted into the applicability of counterfactual explainable AI across both human-centered and science-oriented AI models. Within the context of human-centered AI systems, such as recommender systems, the incorporation of counterfactual explanations can enhance user trust and satisfaction. This is achieved by explaining not only why the system recommends some items, but also what the users can do to change the recommendation results. This approach further enhances user engagement with the system and fosters a more interactive and controllable paradigm for human users.In the scientific field, counterfactual explainable AI offers a valuable contribution. It helps researchers identify key factors behind model predictions in a straightforward manner and promotes trust and credibility in AI-generated outcomes, thereby accelerating both the human comprehension of natural phenomena and the pace of scientific innovation.This dissertation offers a thorough and methodical exploration of counterfactual explainable AI, encompassing its underlying philosophy, stated objectives, methodological framework, practical applications, and evaluation metrics. First, chapter 1 and chapter 2 introduce the core objectives of counterfactual explanations and the attributes that define a high-quality counterfactual explanation. The theoretical foundation is largely based on the Occam's Razor principle. Then, chapter 3 and chapter 4 outline the methodology for generating counterfactual explanations and explore their usage in human-centered applications such as recommender systems. At last, chapter 5 and chapter 6 discuss their use in scientific applications such as molecule property prediction and protein structure prediction, respectively.

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

Mode of access: World Wide Web

ISBN: 9798381741612Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Information retrievalIndex Terms--Genre/Form:

554714
Electronic books.

Explainable AI for Human and Science.
LDR:04198ntm a22003977 4500 001 1145523
005 20240624103716.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798381741612
035 $a (MiAaPQ)AAI30987952
035 $a AAI30987952
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Tan, Juntao. $0 (orcid)0000-0003-3646-933X $3 1437836
245 1 0 $a Explainable AI for Human and Science.
264 0 $c 2024
300 $a 1 online resource (136 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: 85-08, Section: B.
500 $a Advisor: Zhang, Yongfeng.
502 $a Thesis (Ph.D.)--Rutgers The State University of New Jersey, School of Graduate Studies, 2024.
504 $a Includes bibliographical references
520 $a Artificial Intelligence (AI) goes beyond merely making predictions. Its explainability is crucial not only for enhancing user satisfaction but also for facilitating more effective decision-making. Given the remarkable advancements in AI models and their critical roles in both human-centered applications and scientific research in recent years, the demand for explainable AI has never been greater.Among all available methods for achieving explainable AI, this dissertation focuses on the specialized domain of counterfactual explanations. Counterfactual explanations offer a unique interpretation of systems by providing "what-if" scenarios that illuminate how a given outcome could differ if the system input were altered. The model-agnostic nature of counterfactual explanations makes them exceptionally well-suited for elucidating the intrinsic mechanisms of advanced AI systems. This is particularly critical in an era where such systems, especially those employing deep neural networks, are becoming increasingly opaque and complex.An in-depth investigation is conducted into the applicability of counterfactual explainable AI across both human-centered and science-oriented AI models. Within the context of human-centered AI systems, such as recommender systems, the incorporation of counterfactual explanations can enhance user trust and satisfaction. This is achieved by explaining not only why the system recommends some items, but also what the users can do to change the recommendation results. This approach further enhances user engagement with the system and fosters a more interactive and controllable paradigm for human users.In the scientific field, counterfactual explainable AI offers a valuable contribution. It helps researchers identify key factors behind model predictions in a straightforward manner and promotes trust and credibility in AI-generated outcomes, thereby accelerating both the human comprehension of natural phenomena and the pace of scientific innovation.This dissertation offers a thorough and methodical exploration of counterfactual explainable AI, encompassing its underlying philosophy, stated objectives, methodological framework, practical applications, and evaluation metrics. First, chapter 1 and chapter 2 introduce the core objectives of counterfactual explanations and the attributes that define a high-quality counterfactual explanation. The theoretical foundation is largely based on the Occam's Razor principle. Then, chapter 3 and chapter 4 outline the methodology for generating counterfactual explanations and explore their usage in human-centered applications such as recommender systems. At last, chapter 5 and chapter 6 discuss their use in scientific applications such as molecule property prediction and protein structure prediction, respectively.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Computer science. $3 573171
653 $a Information retrieval
653 $a Machine learning
653 $a Decision-making
653 $a Credibility
653 $a Recommender systems
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0464
690 $a 0800
710 2 $a Rutgers The State University of New Jersey, School of Graduate Studies. $b Computer Science. $3 1241263
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-08B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30987952 $z click for full text (PQDT)