Explainable Artificial Intelligence
GPTKB entity
Statements (52)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic
|
gptkbp:abbreviation |
gptkb:XAI
|
gptkbp:application |
gptkb:military
autonomous vehicles finance healthcare legal systems |
gptkbp:challenge |
complexity of deep learning models
lack of standard evaluation metrics trade-off between accuracy and interpretability |
gptkbp:emergedIn |
2010s
|
gptkbp:example |
decision trees
linear regression attention mechanisms prototype-based explanations |
gptkbp:focusesOn |
making AI decisions understandable to humans
|
gptkbp:goal |
enable human oversight
facilitate debugging of AI models increase trust in AI systems |
https://www.w3.org/2000/01/rdf-schema#label |
Explainable Artificial Intelligence
|
gptkbp:importantFor |
gptkb:legislation
AI safety fairness in AI ethical AI user trust |
gptkbp:method |
gptkb:LIME
gptkb:SHAP feature importance counterfactual explanations rule-based explanations saliency maps |
gptkbp:organization |
gptkb:DARPA_XAI_program
gptkb:European_Parliament gptkb:NIST |
gptkbp:publishedIn |
gptkb:Journal_of_Artificial_Intelligence_Research
gptkb:IEEE_Transactions_on_Neural_Networks_and_Learning_Systems gptkb:Nature_Machine_Intelligence |
gptkbp:regulates |
gptkb:GDPR_right_to_explanation
|
gptkbp:relatedConcept |
responsible AI
post-hoc explanation causality in AI inherently interpretable models interpretable machine learning model auditability transparent AI |
gptkbp:relatedTo |
gptkb:Machine_Learning
gptkb:artificial_intelligence Accountability Transparency Interpretability |
gptkbp:bfsParent |
gptkb:David_Gunning
|
gptkbp:bfsLayer |
6
|