Filters








1,159 Hits in 3.2 sec

Argumentative XAI: A Survey [article]

Kristijonas Čyras, Antonio Rago, Emanuele Albini, Pietro Baroni, Francesca Toni
2021 arXiv   pre-print
In this survey we overview XAI approaches built using methods from the field of computational argumentation, leveraging its wide array of reasoning abstractions and explanation delivery methods.  ...  We also lay out a roadmap for future work.  ...  We provide a comprehensive survey of literature in XAI viewing explanations as argumentative (independently of the underlying methods to be explained).  ... 
arXiv:2105.11266v1 fatcat:rnvydntysfa5tdzwzoj52gsac4

A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI [article]

Erico Tjoa, Cuntai Guan
2020 arXiv   pre-print
We provide a review on interpretabilities suggested by different research works and categorize them.  ...  The argumentation theory is implemented in the machine learning training process [155] , extracting arguments or decision rules as the explanations for the prediction of stroke based on the Asymptomatic  ...  Erico T. was also affiliated with HealthTech Division, Alibaba Group Holding Limited. and frameworks to capture interpretability, and the topic explainable artificial intelligence (XAI) has become a hotspot  ... 
arXiv:1907.07374v5 fatcat:ssup2eanlvertbcztuovdakykq

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

Erico Tjoa, Cuntai Guan
2020 IEEE Transactions on Neural Networks and Learning Systems  
We provide a review on interpretabilities suggested by different research works and categorize them.  ...  The argumentation theory is implemented in the ML training process [156] , extracting arguments or decision rules as the explanations for the prediction of stroke based on the asymptomatic carotid stenosis  ...  Popular DL libraries have started to include their own XAI libraries, such as Pytorch Captum and tensorflow tf-explain.  ... 
doi:10.1109/tnnls.2020.3027314 pmid:33079674 fatcat:r7rkyzajbndmnn5ukbqzx4owyi

Argumentative XAI: A Survey

Kristijonas Čyras, Antonio Rago, Emanuele Albini, Pietro Baroni, Francesca Toni
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
In this survey we overview XAI approaches built using methods from the field of computational argumentation, leveraging its wide array of reasoning abstractions and explanation delivery methods.  ...  We also lay out a roadmap for future work.  ...  Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) Survey Track  ... 
doi:10.24963/ijcai.2021/600 fatcat:rftaehqwgjg55ph35foswezk5e

Human-Centered Explainable AI (XAI): From Algorithms to User Experiences [article]

Q. Vera Liao, Kush R. Varshney
2022 arXiv   pre-print
In this chapter, we begin with a high-level overview of the technical landscape of XAI algorithms, then selectively survey our own and other recent HCI works that take human-centered approaches to design  ...  As a technical sub-field of artificial intelligence (AI), explainable AI (XAI) has produced a vast collection of algorithms, providing a toolbox for researchers and practitioners to build XAI applications  ...  In this chapter we provide a selected survey on work from this emerging community to encourage future research to continue bridging design practices and state-of-the-art XAI techniques, uncovering pitfalls  ... 
arXiv:2110.10790v4 fatcat:elmw4vwnmbafvlucuneyqrp2rq

The Pragmatic Turn in Explainable Artificial Intelligence (XAI)

Andrés Páez
2019 Minds and Machines  
Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models  ...  But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will lack a well-defined goal.  ...  survey of recent characterizations of the goals of XAI, see Lipton (2016), Doshi-Velez & Kim (2017), Samek et al. (2017), and Gilpin et al. (2019).  ... 
doi:10.1007/s11023-019-09502-w fatcat:4h4pyhwocbdvfcm6cnk5pn7aaa

Measure Utility, Gain Trust: Practical Advice for XAI Researcher [article]

Brittany Davis, Maria Glenski, William Sealy, Dustin Arendt
2020 arXiv   pre-print
., explainable AI (XAI), has seen a commensurate exponential growth alongside deep artificial neural networks throughout the past decade.  ...  To address this, we contribute a practical path forward for researchers in the XAI field. We recommend researchers focus on the utility of machine learning explanations instead of trust.  ...  The next section of this paper will provide historical context for this argument.  ... 
arXiv:2009.12924v1 fatcat:ewnhbsb7obcita5qzcwam4rneq

Deep Argumentative Explanations [article]

Emanuele Albini, Piyawat Lertvittayakumjorn, Antonio Rago, Francesca Toni
2021 arXiv   pre-print
notions from computational argumentation, a form of symbolic AI offering useful reasoning abstractions for explanation.  ...  that also have an argumentative spirit.  ...  Morgan or its a liates. This material is not a product of the Research Department of J.P. Morgan Securities LLC.  ... 
arXiv:2012.05766v4 fatcat:66qelbm4wzenzbfxllqckxswza

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI [article]

Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, Salvador García, Sergio Gil-López, Daniel Molina, Richard Benjamins, Raja Chatila, Francisco Herrera
2019 arXiv   pre-print
This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached.  ...  This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability.  ...  Since explaining, as argumenting, may involve weighting, comparing or convincing an audience with logic-based formalizations of (counter) arguments [28] , explainability might convey us into the realm  ... 
arXiv:1910.10045v2 fatcat:hgoi7cvkazdd5jycsdfkn565di

To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods

Elvio Amparore, Alan Perotti, Paolo Bajardi
2021 PeerJ Computer Science  
Among the many approaches to XAI, a widely adopted paradigm is Local Linear Explanations—with LIME and SHAP emerging as state-of-the-art methods.  ...  The main objective of eXplainable Artificial Intelligence (XAI) is to provide effective explanations for black-box classifiers.  ...  second opinion without an argument to support it, or a measurable score of trust (Jiang et al., 2018) .  ... 
doi:10.7717/peerj-cs.479 pmid:33977131 pmcid:PMC8056245 fatcat:ltbymvindjc3doo2g77uugla3y

Evaluating XAI: A comparison of rule-based and example-based explanations

Jasper van der Waa, Elisabeth Nieuwburg, Anita Cremers, Mark Neerincx
2020 Artificial Intelligence  
Current developments in Artificial Intelligence (AI) led to a resurgence of Explainable AI (XAI).  ...  New XAI methods are often based on an intuitive notion what an effective explanation should be. Rule-and example-based contrastive explanations are two exemplary explanation styles.  ...  A third survey by [4] discusses an explicit issue with user evaluations in XAI.  ... 
doi:10.1016/j.artint.2020.103404 fatcat:gdxqjfp4c5falcnjznrrkjjarm

A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems [article]

Sina Mohseni and Niloofar Zarei and Eric D. Ragan
2020 arXiv   pre-print
To this end, this paper presents a survey and framework intended to share knowledge and experiences of XAI design and evaluation methods across multiple disciplines.  ...  , we present a categorization of interpretable machine learning design goals and evaluation methods to show a mapping between design goals for different XAI user groups and their evaluation methods.  ...  The work in this paper is supported by the DARPA XAI program under N66001-17-2-4031 and by NSF award 1900767.  ... 
arXiv:1811.11839v5 fatcat:pl4mmtd2zzhipilebnc2khagu4

Factors causing design changes in Vietnamese residential construction projects: An evaluation and comparison

Ha Duy Khanh
2020 Tạp chí Khoa học Công nghệ Xây dựng (KHCNXD) - ĐHXD  
These changes have a significant impact on the time and cost of the project.  ...  This study has used a questionnaire to collect data for the occurrence and effect of these factors on project performance.  ...  [8] indicated several different impacts of design changes, including low motivation, quality differences, and legal arguments. -Love and Edwards [30] , and Yap et al.  ... 
doi:10.31814/10.31814/stce.nuce2020-14(3)-13 fatcat:taqlurnt35hjrdozqqxqme4hde

Aristotle's "Second Man" Argument

Theodore Scaltsas
1993 Phronesis: A Journal for Ancient Philosophy  
His argument in Z, 6 is a reductio ad absurdum of the claim that a thing's essence is different from that thing.  ...  It is a regress argument which, despite its centrality, has not attracted anywhere near the attention that the Third Man Argument commands in the literature, probably because it seems to be a straightforward  ...  Alexander says: "uL X(Ok' A [LT) EU iV EXCTOV Tov UTOV ELVCL xai TO TI Lv EIVTL oErTw, ci&a ?T noXkXa TOjiTO E?  ... 
doi:10.1163/156852893321052352 fatcat:b4cobxv7wna35gihqyyfaecviu

XÂY DỰNG HOẠT ĐỘNG DẠY HỌC BIỂU ĐỒ THỐNG KÊ TRONG CHƯƠNG TRÌNH GIÁO DỤC PHỔ THÔNG MÔN TOÁN 2018 CHO BẬC TRUNG HỌC CƠ SỞ

Nguyễn Thị Diệu, Lê Thái Bảo Thiên Trung
2020 Tạp chí Khoa học  
Hơn nữa, một quy trình thiết kế dạy học được chúng tôi xây dựng, vận dụng trong nghiên cứu này và đúc kết thành những nội dung dạy học phù hợp.  ...  The following is a survey of the favorite sport of class 8A 1) With the above data, should you use the picture chart to represent the data? Explain why?  ...  Therefore, establishing arguments to protect or adjust opinions.  ... 
doi:10.54607/hcmue.js.17.5.2716(2020) fatcat:si5egbza5fhmdbdlbetyj3dszm
« Previous Showing results 1 — 15 out of 1,159 results