Statements (35)
Predicate | Object |
---|---|
gptkbp:instanceOf |
field of artificial intelligence
|
gptkbp:alsoKnownAs |
gptkb:XAI
|
gptkbp:appliesTo |
gptkb:machine_learning
deep learning |
gptkbp:challenge |
complexity of AI models
trade-off between accuracy and interpretability |
gptkbp:emergedIn |
2010s
|
gptkbp:focusesOn |
making AI decisions understandable to humans
|
gptkbp:goal |
enable human oversight
improve trust in AI increase transparency of AI systems |
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:motive |
regulatory requirements
ethical concerns user trust |
gptkbp:relatedTo |
ethics in AI
accountability in AI fairness in AI interpretable machine learning |
gptkbp:standardizedBy |
gptkb:DARPA_XAI_program
gptkb:IEEE_standards gptkb:EU_AI_Act |
gptkbp:usedIn |
autonomous vehicles
finance healthcare legal systems government decision-making |
gptkbp:bfsParent |
gptkb:Song_Chun
|
gptkbp:bfsLayer |
7
|