|
gptkbp:instanceOf
|
artificial intelligence concept
|
|
gptkbp:alsoKnownAs
|
gptkb:XAI
|
|
gptkbp:appliesTo
|
deep learning
machine learning models
|
|
gptkbp:category
|
gptkb:artificial_intelligence
gptkb:machine_learning
computer science
ethics in technology
|
|
gptkbp:challenge
|
complexity of AI models
lack of standard metrics
trade-off with accuracy
|
|
gptkbp:emergedIn
|
2010s
|
|
gptkbp:enables
|
gptkb:legislation
accountability
trust in AI systems
|
|
gptkbp:focusesOn
|
transparency
interpretability
understandability
|
|
gptkbp:goal
|
make AI decisions understandable to humans
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
explainable AI
|
|
gptkbp:method
|
gptkb:LIME
gptkb:SHAP
feature importance
counterfactual explanations
rule-based explanations
saliency maps
|
|
gptkbp:promotion
|
gptkb:European_Union_AI_Act
gptkb:US_National_Institute_of_Standards_and_Technology_(NIST)
|
|
gptkbp:relatedTo
|
ethics in AI
fairness in AI
responsible AI
|
|
gptkbp:studiedBy
|
gptkb:DARPA_XAI_program
gptkb:Google
gptkb:IBM
gptkb:Microsoft
gptkb:OpenAI
academic institutions
|
|
gptkbp:usedIn
|
gptkb:government
autonomous vehicles
finance
healthcare
legal systems
|
|
gptkbp:bfsParent
|
gptkb:Machine_Learning
gptkb:knowledge_representation
gptkb:CVPR
gptkb:Vertex_AI
gptkb:Klaus-Robert_Müller
|
|
gptkbp:bfsLayer
|
5
|