Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897795158> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W2897795158 abstract "Explaining the results of data-intensive computation via provenance has been extensively studied in the literature. We focus here on explaining the output of Machine Learning Classifiers, which are main components of many contemporary Data Science applications. We have developed a simple generic approach for explaining classification results, by looking for constrained perturbations to parts of the input that would have the most significant effect on the classification. Our solution requires white-box access to the model internals and a specification of constraints that define which perturbations are reasonable in the application domain; both are typically available to the data scientist. We propose to demonstrate CEC, a system prototype that is based on these foundations to provide generic explanations for Neural Networks and Random Forests. We will demonstrate the system usefulness in the context of two application domains: bank marketing campaigns, and visually clear explanations for image classifications. We will highlight the benefit that such explanations could yield to the data scientist and interactively engage the audience in computing and viewing explanations for different cases and different sets of constraints." @default.
- W2897795158 created "2018-10-26" @default.
- W2897795158 creator A5010359061 @default.
- W2897795158 creator A5073835385 @default.
- W2897795158 date "2018-10-17" @default.
- W2897795158 modified "2023-09-24" @default.
- W2897795158 title "CEC" @default.
- W2897795158 cites W2047182010 @default.
- W2897795158 cites W2108598243 @default.
- W2897795158 cites W2124026371 @default.
- W2897795158 cites W2130486630 @default.
- W2897795158 cites W2183341477 @default.
- W2897795158 cites W2282821441 @default.
- W2897795158 cites W2293768274 @default.
- W2897795158 cites W2510508396 @default.
- W2897795158 cites W2919115771 @default.
- W2897795158 doi "https://doi.org/10.1145/3269206.3269214" @default.
- W2897795158 hasPublicationYear "2018" @default.
- W2897795158 type Work @default.
- W2897795158 sameAs 2897795158 @default.
- W2897795158 citedByCount "3" @default.
- W2897795158 countsByYear W28977951582019 @default.
- W2897795158 countsByYear W28977951582020 @default.
- W2897795158 countsByYear W28977951582023 @default.
- W2897795158 crossrefType "proceedings-article" @default.
- W2897795158 hasAuthorship W2897795158A5010359061 @default.
- W2897795158 hasAuthorship W2897795158A5073835385 @default.
- W2897795158 hasConcept C41008148 @default.
- W2897795158 hasConceptScore W2897795158C41008148 @default.
- W2897795158 hasFunder F4320338335 @default.
- W2897795158 hasLocation W28977951581 @default.
- W2897795158 hasOpenAccess W2897795158 @default.
- W2897795158 hasPrimaryLocation W28977951581 @default.
- W2897795158 hasRelatedWork W2049775471 @default.
- W2897795158 hasRelatedWork W2093578348 @default.
- W2897795158 hasRelatedWork W2350741829 @default.
- W2897795158 hasRelatedWork W2358668433 @default.
- W2897795158 hasRelatedWork W2376932109 @default.
- W2897795158 hasRelatedWork W2382290278 @default.
- W2897795158 hasRelatedWork W2390279801 @default.
- W2897795158 hasRelatedWork W2748952813 @default.
- W2897795158 hasRelatedWork W2899084033 @default.
- W2897795158 hasRelatedWork W3004735627 @default.
- W2897795158 isParatext "false" @default.
- W2897795158 isRetracted "false" @default.
- W2897795158 magId "2897795158" @default.
- W2897795158 workType "article" @default.