Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080988227> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3080988227 abstract "There is an increasing demand for quality assurance of machine learning (ML) models as more and more ML applications are investigated in various domains. This means that we need to explicitly take account of the requirements and environmental assumptions for quality evaluation and improvement of ML models. The traditional approach has been performance evaluation, typically in accuracy, for the target dataset. However, this approach only focuses on the global accuracy over the whole dataset and obfuscates performance for individual specific aspects in the requirements and environmental assumptions. We then lack insights necessary to deal with high-priority requirements and to detect risks or weaknesses in specific situations. In response to this problem, we investigate a testing method based on attributes that capture aspects in the requirements and environmental assumptions. We divide the input space into explicit and explainable sub-spaces, which allows the divide-and-conquer style in a granular manner as we have done for traditional software testing. We demonstrate our method with simple attributes for CIFAR-10 and BDD100K datasets." @default.
- W3080988227 created "2020-09-01" @default.
- W3080988227 creator A5006003592 @default.
- W3080988227 creator A5060475153 @default.
- W3080988227 creator A5061154995 @default.
- W3080988227 date "2020-08-01" @default.
- W3080988227 modified "2023-09-26" @default.
- W3080988227 title "Attribute-based Granular Evaluation for Performance of Machine Learning Models" @default.
- W3080988227 cites W2110441383 @default.
- W3080988227 cites W2324595780 @default.
- W3080988227 cites W2511730936 @default.
- W3080988227 cites W2543296129 @default.
- W3080988227 cites W2612445135 @default.
- W3080988227 cites W2616028256 @default.
- W3080988227 cites W2736941579 @default.
- W3080988227 cites W2796438033 @default.
- W3080988227 cites W2799352588 @default.
- W3080988227 cites W2803850896 @default.
- W3080988227 cites W2809701591 @default.
- W3080988227 cites W2859484040 @default.
- W3080988227 cites W2885659818 @default.
- W3080988227 cites W2945883466 @default.
- W3080988227 cites W2949650786 @default.
- W3080988227 cites W2963327228 @default.
- W3080988227 cites W2963913218 @default.
- W3080988227 cites W3006197148 @default.
- W3080988227 cites W3118608800 @default.
- W3080988227 cites W3163244177 @default.
- W3080988227 doi "https://doi.org/10.1109/aitest49225.2020.00026" @default.
- W3080988227 hasPublicationYear "2020" @default.
- W3080988227 type Work @default.
- W3080988227 sameAs 3080988227 @default.
- W3080988227 citedByCount "0" @default.
- W3080988227 crossrefType "proceedings-article" @default.
- W3080988227 hasAuthorship W3080988227A5006003592 @default.
- W3080988227 hasAuthorship W3080988227A5060475153 @default.
- W3080988227 hasAuthorship W3080988227A5061154995 @default.
- W3080988227 hasConcept C106436119 @default.
- W3080988227 hasConcept C111472728 @default.
- W3080988227 hasConcept C111919701 @default.
- W3080988227 hasConcept C11413529 @default.
- W3080988227 hasConcept C119857082 @default.
- W3080988227 hasConcept C124101348 @default.
- W3080988227 hasConcept C127413603 @default.
- W3080988227 hasConcept C138885662 @default.
- W3080988227 hasConcept C154945302 @default.
- W3080988227 hasConcept C199360897 @default.
- W3080988227 hasConcept C21547014 @default.
- W3080988227 hasConcept C2777904410 @default.
- W3080988227 hasConcept C2778572836 @default.
- W3080988227 hasConcept C2778618615 @default.
- W3080988227 hasConcept C2779530757 @default.
- W3080988227 hasConcept C2780586882 @default.
- W3080988227 hasConcept C41008148 @default.
- W3080988227 hasConcept C63882131 @default.
- W3080988227 hasConcept C71559656 @default.
- W3080988227 hasConceptScore W3080988227C106436119 @default.
- W3080988227 hasConceptScore W3080988227C111472728 @default.
- W3080988227 hasConceptScore W3080988227C111919701 @default.
- W3080988227 hasConceptScore W3080988227C11413529 @default.
- W3080988227 hasConceptScore W3080988227C119857082 @default.
- W3080988227 hasConceptScore W3080988227C124101348 @default.
- W3080988227 hasConceptScore W3080988227C127413603 @default.
- W3080988227 hasConceptScore W3080988227C138885662 @default.
- W3080988227 hasConceptScore W3080988227C154945302 @default.
- W3080988227 hasConceptScore W3080988227C199360897 @default.
- W3080988227 hasConceptScore W3080988227C21547014 @default.
- W3080988227 hasConceptScore W3080988227C2777904410 @default.
- W3080988227 hasConceptScore W3080988227C2778572836 @default.
- W3080988227 hasConceptScore W3080988227C2778618615 @default.
- W3080988227 hasConceptScore W3080988227C2779530757 @default.
- W3080988227 hasConceptScore W3080988227C2780586882 @default.
- W3080988227 hasConceptScore W3080988227C41008148 @default.
- W3080988227 hasConceptScore W3080988227C63882131 @default.
- W3080988227 hasConceptScore W3080988227C71559656 @default.
- W3080988227 hasLocation W30809882271 @default.
- W3080988227 hasOpenAccess W3080988227 @default.
- W3080988227 hasPrimaryLocation W30809882271 @default.
- W3080988227 hasRelatedWork W137124525 @default.
- W3080988227 hasRelatedWork W1486246673 @default.
- W3080988227 hasRelatedWork W1639590351 @default.
- W3080988227 hasRelatedWork W2021621568 @default.
- W3080988227 hasRelatedWork W2398582103 @default.
- W3080988227 hasRelatedWork W2588156333 @default.
- W3080988227 hasRelatedWork W2961085424 @default.
- W3080988227 hasRelatedWork W3129894253 @default.
- W3080988227 hasRelatedWork W4286629047 @default.
- W3080988227 hasRelatedWork W4224009465 @default.
- W3080988227 isParatext "false" @default.
- W3080988227 isRetracted "false" @default.
- W3080988227 magId "3080988227" @default.
- W3080988227 workType "article" @default.