Results 241 to 250 of about 55,142 (282)

Designing effective explainable AI: a human-centered evaluation of explanation formats in financial decision-making. [PDF]

Front Artif Intell
Maathuis H, Stalenhoef M, van Otterloo S, Zwaal R, van Montfort K, Sent D.   +5 more
europepmc   +1 more source

XAI with BlackBox

openaire   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

XAI in Biomedical Applications

2023
When the correct diagnosis or selection of therapy is made by algorithms by a machine, decisions for doctors, patients, and experts can become non-transparent, leading to the breakdown of relationships. Asking the machine to explain its algorithms is essentially a detailed understanding of the mathematical and statistical details.
Kirboğa, K.K., Küçüksille, E.U.
openaire   +2 more sources

Actionable XAI for the Fuzzy Integral

2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2021
The adoption of artificial intelligence (AI) into domains that impact human life (healthcare, agriculture, security and defense, etc.) has led to an increased demand for explainable AI (XAI). Herein, we focus on an under represented piece of the XAI puzzle, information fusion.
Bryce Murray, Derek T. Anderson, Timothy C. Havens   +2 more
openaire   +1 more source

Quality of artisan production yoghurt in the communities of the district of Xai-Xai

International Journal of Life Science Research Archive, 2022
Yogurt is a product derived from milk fermented by the action of lactic bacteria (Lactobacillus bulgaricus and Streptococcus thermophilus) that use part of the lactose, transforming into lactic acid and aromatic compounds that characterize yogurt.
null Abel Alberto Massingue Júnior, null António Elísio José   +1 more
openaire   +1 more source

XAI for Communication Networks

2022 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), 2022
Sayandev Mukherjee, Jason W. Rupe, Jingjie Zhu   +2 more
openaire   +1 more source

XAI for unsupervised learning

Unsupervised learning algorithms detect inherent patterns and relationships in data without requiring predefined target variables. Although unsupervised learning algorithms have great capabilities, their decisions remain largely opaque, driving the need for explainability.
openaire   +2 more sources

XAI in Drug Discovery

[No abstract available]
openaire   +2 more sources