Results 41 to 50 of about 83,581 (168)
Informatik-Spektrum, 2018 ,,Explainable AI“ ist kein neues Gebiet. Vielmehr ist das Problem der Erklarbarkeit so alt wie die AI selbst, ja vielmehr das Resultat ihrer selbst. Wahrend regelbasierte Losungen der fruhen AI nachvollziehbare ,,Glass-Box“-Ansatze darstellten, lag deren Schwache im Umgang mit Unsicherheiten der realen Welt.
openaire +1 more source
What Does Explainable AI Really Mean? A New Conceptualization of Perspectives [PDF]
, 2017 We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and ...
Besold, T. R., Doran, D., Schulz, S.C.
core +2 more sources
Explainable AI improves task performance in human–AI collaboration
Scientific ReportsArtificial intelligence (AI) provides considerable opportunities to assist human work. However, one crucial challenge of human–AI collaboration is that many AI algorithms operate in a black-box manner where the way how the AI makes predictions remains ...
Julian Senoner +4 more
doaj +1 more source
Implications of causality in artificial intelligence
Frontiers in Artificial IntelligenceOver the last decade, investment in artificial intelligence (AI) has grown significantly, driven by technology companies and the demand for PhDs in AI. However, new challenges have emerged, such as the ‘black box’ and bias in AI models.
Luís Cavique
doaj +1 more source
Medically-oriented design for explainable AI for stress prediction from physiological measurements
BMC Medical Informatics and Decision Making, 2022 Background In the last decade, a lot of attention has been given to develop artificial intelligence (AI) solutions for mental health using machine learning.
Dalia Jaber +3 more
doaj +1 more source
Explaining Machines: Social Management of Incomprehensible Algorithms. Introduction
Sociologica, 2023 This short introduction presents the symposium ‘Explaining Machines’. It locates the debate about Explainable AI in the history of the reflection about AI and outlines the issues discussed in the contributions.
Elena Esposito
doaj +1 more source
An Interpretable Machine Vision Approach to Human Activity Recognition using Photoplethysmograph Sensor Data [PDF]
, 2018 The current gold standard for human activity recognition (HAR) is based on the use of cameras. However, the poor scalability of camera systems renders them impractical in pursuit of the goal of wider adoption of HAR in mobile computing contexts ...
Brophy, Eoin +4 more
core +1 more source
Proceedings of the Conference on Fairness, Accountability, and Transparency, 2019 Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might
Mittelstadt, BD, Russell, C, Wachter, S
openaire +5 more sources
The effectiveness of explainable AI on human factors in trust models
Scientific ReportsExplainable AI has garnered significant traction in science communication research. Prior empirical studies have firmly established that explainable AI communication could improve trust in AI and that trust in AI engineers was argued to be an under ...
Justin C. Cheung, Shirley S. Ho
doaj +1 more source
International Review of Research in Open and Distributed LearningThis study examined an online professional development program integrating artificial intelligence (AI) literacy into mathematics instruction through unplugged, explainable machine-learning activities.
Woonhee Sung, Yasemin Gunpinar
doaj +1 more source