5,747 Hits in 3.4 sec

The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies [article]

Aniek F. Markus, Jan A. Kors, Peter R. Rijnbeek
2020 arXiv   pre-print
We argue the reason to demand explainability determines what should be explained as this determines the relative importance of the properties of explainability (i.e. interpretability and fidelity).  ...  Artificial intelligence (AI) has huge potential to improve the health and well-being of people, but adoption in clinical practice is still limited.  ...  Acknowledgements The authors like to thank Dr. Jenna Reps for her valuable feedback on this manuscript.  ... 
arXiv:2007.15911v1 fatcat:hcupk4qssbaslf2wj7rmxj7r5e

Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations [article]

Fabian Sperrle, Mennatallah El-Assady, Grace Guo, Duen Horng Chau, Alex Endert, Daniel Keim
2020 arXiv   pre-print
This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches.  ...  Furthermore, we identify and discuss the potential for future work based on observed research gaps that should lead to better coverage of the proposed model.  ...  Explainable Artificial Intelligence (XAI) is the study of making the decision-making processes of AI models explainable.  ... 
arXiv:2009.06433v1 fatcat:fwlxnyaymvdfnfjqpkf7phtfmy

Artificial Paranoia

Kenneth Mark Colby, Sylvia Weber, Franklin Dennis Hilf
1971 Artificial Intelligence  
Within the paradigm of computer science, distinctions are sometimes drawn between the activities of computer simulation and artificial intelligence.  ...  Yet in constructing models of psychological processes, the distinction can become blurred in places where overlaps emerge, as will be evident from our account of a model of artificial paranoia. I.  ...  Some topics have an alternate default response, for the purpose of avoiding repetition.  ... 
doi:10.1016/0004-3702(71)90002-6 fatcat:zsd2ndfnlbaq5a75y3drx36uea

Transparency you can trust: Transparency requirements for artificial intelligence between legal norms and contextual concerns

Heike Felzmann, Eduard Fosch Villaronga, Christoph Lutz, Aurelia Tamò-Larrieux
2019 Big Data & Society  
This relational concept of transparency points to future research directions for the study of transparency in artificial intelligence systems and should be taken into account in policymaking.  ...  We show that human–computer interaction and human-robot interaction literature do not provide clear results with respect to the benefits of transparency for users of artificial intelligence technologies  ...  The authors are listed in alphabetical order and have contributed equally to this article  ... 
doi:10.1177/2053951719860542 fatcat:ckdhn6jj3zdntpfhcpglp75yee

Online Dating Meets Artificial Intelligence: How the Perception of Algorithmically Generated Profile Text Impacts Attractiveness and Trust

Yihan Wu, Ryan M. Kelly
2020 32nd Australian Conference on Human-Computer Interaction  
Artificial intelligence (AI) has the potential to help online daters by automatically generating profile content, but little research has explored how the use of AI in online dating could affect users'  ...  We interpret our findings through the lens of social information processing theory, discussing the tradeoffs associated with designing to reveal or hide the use of AI in online dating.  ...  ACKNOWLEDGMENTS We thank the reviewers for comments and suggestions that improved this paper.  ... 
doi:10.1145/3441000.3441074 fatcat:vglnafgimjgtve6gvdkb2wv57q

Explainable Artificial Intelligence for Digital Forensics: Opportunities, Challenges and a Drug Testing Case Study [chapter]

Louise Kelly, Swati Sachan, Lei Ni, Fatima Almaghrabi, Richard Allmendinger, Yu-Wang Chen
2020 Digital Forensic Science [Working Title]  
To this end, this book chapter investigates the opportunities and challenges of developing interactive and eXplainable Artificial Intelligence (XAI) systems to support digital forensics and automate the  ...  It could become an extremely powerful tool for helping judges and jurors make decisions in the presence of many interconnected pieces of evidence.  ...  It will discuss the opportunity to utilise the forensic data to develop an interpretable and trustworthy system for automation of the decision-making process [68] [69] [70] [71] [72] [73] [74] [75] [76  ... 
doi:10.5772/intechopen.93310 fatcat:scjt4yyqdvdnzcokvuecanuwuu

Personalized medicine, digital technology and trust: a Kantian account

Bjørn K. Myskja, Kristin S. Steinsbekk
2020 Medicine, Health care and Philosophy  
as the accountable gate-keeper taking moral responsibility required for an active, reflexive trust.  ...  The ideal is to increase wellness by minimizing the layer of interpretation and translation between relevant health information and the patient or user.  ...  An important part of this picture is using the potential of artificial intelligence-machine learning-to make sense of these huge amounts of data (Moore et al. 2019; Mesko 2017; Miller and Brown 2018)  ... 
doi:10.1007/s11019-020-09974-z pmid:32888101 fatcat:6qado2jdm5bhvg4bdbqw3dov2y

The Challenges and Opportunities of Human-Centered AI for Trustworthy Robots and Autonomous Systems [article]

Hongmei He, John Gray, Angelo Cangelosi, Qinggang Meng, T.Martin McGinnity, Jörn Mehnen
2021 arXiv   pre-print
Hence, a new acceptance model of RAS is provided, as a framework for requirements to human-centered AI and for implementing trustworthy RAS by design.  ...  This research systematically explores, for the first time, the key facets of human-centered AI (HAI) for trustworthy RAS.  ...  As a minimum, the "Design for Error" principles [13] should assume that faults will occur and provide appropriate scope for human interventions, where an "error" is broadly interpreted as any set of  ... 
arXiv:2105.04408v1 fatcat:jvlx7lkjizgnbcu2t27ndi4l3q

The Role of Normware in Trustworthy and Explainable AI [article]

Giovanni Sileno, Alexander Boer, Tom van Engers
2018 arXiv   pre-print
to these issues, and argues for its irreducibility with respect to software by making explicit its neglected ecological dimension in the decision-making cycle.  ...  Reorganizing ideas and discussions presented in AI and related fields, this position paper aims to highlight the importance of normware--that is, computational artifacts specifying norms--with respect  ...  This offers an explaination of why ML is particularly vulnerable to explainable and trustworthy AI issues.  ... 
arXiv:1812.02471v1 fatcat:cvl6lbvxtbbwdlmnvg5v34atam

Beneficial AI: the next battlefield

Eugénio Oliveira
2018 Journal of Innovation Management  
Intelligence, ART standing for Accountability, Responsibility and Transparency, becomes also mandatory for trustworthy AI-based systems.This letter is an abbreviation of a more substantial article to  ...  An "Artificial Intelligence-first" world is being preached all over the media by many responsible players in economic and scientific communities.This letter states our belief in AI potentialities, including  ...  Is awareness the acknowledgment of Self? How to define the Self?  ... 
doi:10.24840/2183-0606_005.004_0002 fatcat:3ury3fgaz5duvm6bgwbn6rwtuy

Explainable AI for B5G/6G: Technical Aspects, Use Cases, and Research Challenges [article]

Shen Wang, M.Atif Qureshi, Luis Miralles-Pechuaán, Thien Huynh-The, Thippa Reddy Gadekallu, Madhusanka Liyanage
2021 arXiv   pre-print
Researchers expect 6G to have higher bandwidth, coverage, reliability, energy efficiency, lower latency, and, more importantly, an integrated "human-centric" network system powered by artificial intelligence  ...  These decisions can range widely, from network resource allocation to collision avoidance for self-driving cars.  ...  In contrast, GDPR that can be used to judge the explainability of AI decisions gives more to an individual instead of looking at it [239].  ... 
arXiv:2112.04698v1 fatcat:y7ss4opmrjbsbjm3ip2vgkkgky

Perceptions of Fairness and Trustworthiness Based on Explanations in Human vs. Automated Decision-Making [article]

Jakob Schoeffer, Yvette Machowski, Niklas Kuehl
2021 arXiv   pre-print
In this work, we conduct an online study with 200 participants to examine people's perceptions of fairness and trustworthiness towards ADS in comparison to a scenario where a human instead of an ADS makes  ...  Those systems typically involve sophisticated yet opaque artificial intelligence (AI) techniques that seldom allow for full comprehension of their inner workings, particularly for affected individuals.  ...  H2 People's perceptions of trustworthiness are higher when they are told the decision-maker is a human as compared to an ADS.  ... 
arXiv:2109.05792v1 fatcat:uagdznuyrnf33erglaa5zfwykm

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
The need for interpretable and accountable intelligent systems grows along with the prevalence of artificial intelligence applications used in everyday life.  ...  Explainable intelligent systems are designed to self-explain the reasoning behind system decisions and predictions, and researchers from different disciplines work together to define, design, and evaluate  ...  The views and conclusions in this paper are those of the authors and should not be interpreted as representing any funding agencies.  ... 
arXiv:1811.11839v5 fatcat:pl4mmtd2zzhipilebnc2khagu4

In AI We Trust Incrementally: a Multi-layer Model of Trust to Analyze Human-Artificial Intelligence Interactions

Andrea Ferrario, Michele Loi, Eleonora Viganò
2019 Philosophy & Technology  
Real engines of the artificial intelligence (AI) revolution, machine learning (ML) models, and algorithms are embedded nowadays in many services and products around us.  ...  in human-AI interactions in an example of relevance for business organizations.  ...  For example, due to the existence of a certain number of past positive interactions between X and Y, X has collected information that she considers sufficient for judging Y trustworthy and, as a result  ... 
doi:10.1007/s13347-019-00378-3 fatcat:7rtpyupt2zgvdfjshkdledqx4q

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

Knud Thomsen
2021 AI  
The Ouroboros Model has been proposed as a biologically-inspired comprehensive cognitive architecture for general intelligence, comprising natural and artificial manifestations.  ...  The approach addresses very diverse fundamental desiderata of research in natural cognition and also artificial intelligence, AI.  ...  Acknowledgments: A number of knowledgeable and thought-provoking comments and questions by three anonymous reviewers as well as excellent support by the editor are gratefully acknowledged.  ... 
doi:10.3390/ai2010007 fatcat:hhhlnbzg6jhb5om7osi2wogwme
« Previous Showing results 1 — 15 out of 5,747 results