FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805897895> ?p ?o ?g. }

• W2805897895 abstract "The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes. In this paper, we propose an approach to generate such explanations in which training data is augmented to include, in addition to features and labels, explanations elicited from domain users. A joint model is then learned to produce both labels and explanations from the input features. This simple idea ensures that explanations are tailored to the complexity expectations and domain knowledge of the consumer. Evaluation spans multiple modeling techniques on a game dataset, a (visual) aesthetics dataset, a chemical odor dataset and a Melanoma dataset showing that our approach is generalizable across domains and algorithms. Results demonstrate that meaningful explanations can be reliably taught to machine learning algorithms, and in some cases, also improve modeling accuracy." @default.
• W2805897895 created "2018-06-13" @default.
• W2805897895 creator A5015286159 @default.
• W2805897895 creator A5045892503 @default.
• W2805897895 creator A5048793009 @default.
• W2805897895 creator A5055240660 @default.
• W2805897895 creator A5072597892 @default.
• W2805897895 creator A5073027533 @default.
• W2805897895 creator A5077627355 @default.
• W2805897895 creator A5081874896 @default.
• W2805897895 date "2018-05-29" @default.
• W2805897895 modified "2023-09-23" @default.
• W2805897895 title "Teaching Meaningful Explanations" @default.
• W2805897895 cites W1825675169 @default.
• W2805897895 cites W1965701254 @default.
• W2805897895 cites W1994606570 @default.
• W2805897895 cites W1996796871 @default.
• W2805897895 cites W2041029272 @default.
• W2805897895 cites W2047956997 @default.
• W2805897895 cites W2091144449 @default.
• W2805897895 cites W2123229215 @default.
• W2805897895 cites W2153332911 @default.
• W2805897895 cites W2162096170 @default.
• W2805897895 cites W2282821441 @default.
• W2805897895 cites W2294946151 @default.
• W2805897895 cites W2295107390 @default.
• W2805897895 cites W2417288846 @default.
• W2805897895 cites W2440159969 @default.
• W2805897895 cites W2467510144 @default.
• W2805897895 cites W2519809734 @default.
• W2805897895 cites W2558888286 @default.
• W2805897895 cites W2589330732 @default.
• W2805897895 cites W2594475271 @default.
• W2805897895 cites W2610018085 @default.
• W2805897895 cites W2617799811 @default.
• W2805897895 cites W2657631929 @default.
• W2805897895 cites W2670253439 @default.
• W2805897895 cites W2724701856 @default.
• W2805897895 cites W2734754183 @default.
• W2805897895 cites W2744283806 @default.
• W2805897895 cites W2774522520 @default.
• W2805897895 cites W2807551884 @default.
• W2805897895 cites W2911964244 @default.
• W2805897895 cites W2949467366 @default.
• W2805897895 cites W2963946669 @default.
• W2805897895 cites W3104119469 @default.
• W2805897895 cites W3123686114 @default.
• W2805897895 cites W3124443940 @default.
• W2805897895 hasPublicationYear "2018" @default.
• W2805897895 type Work @default.
• W2805897895 sameAs 2805897895 @default.
• W2805897895 citedByCount "7" @default.
• W2805897895 countsByYear W28058978952018 @default.
• W2805897895 countsByYear W28058978952019 @default.
• W2805897895 countsByYear W28058978952020 @default.
• W2805897895 crossrefType "posted-content" @default.
• W2805897895 hasAuthorship W2805897895A5015286159 @default.
• W2805897895 hasAuthorship W2805897895A5045892503 @default.
• W2805897895 hasAuthorship W2805897895A5048793009 @default.
• W2805897895 hasAuthorship W2805897895A5055240660 @default.
• W2805897895 hasAuthorship W2805897895A5072597892 @default.
• W2805897895 hasAuthorship W2805897895A5073027533 @default.
• W2805897895 hasAuthorship W2805897895A5077627355 @default.
• W2805897895 hasAuthorship W2805897895A5081874896 @default.
• W2805897895 hasConcept C111472728 @default.
• W2805897895 hasConcept C119857082 @default.
• W2805897895 hasConcept C134306372 @default.
• W2805897895 hasConcept C138885662 @default.
• W2805897895 hasConcept C154945302 @default.
• W2805897895 hasConcept C207685749 @default.
• W2805897895 hasConcept C2522767166 @default.
• W2805897895 hasConcept C2780586882 @default.
• W2805897895 hasConcept C33923547 @default.
• W2805897895 hasConcept C36503486 @default.
• W2805897895 hasConcept C41008148 @default.
• W2805897895 hasConceptScore W2805897895C111472728 @default.
• W2805897895 hasConceptScore W2805897895C119857082 @default.
• W2805897895 hasConceptScore W2805897895C134306372 @default.
• W2805897895 hasConceptScore W2805897895C138885662 @default.
• W2805897895 hasConceptScore W2805897895C154945302 @default.
• W2805897895 hasConceptScore W2805897895C207685749 @default.
• W2805897895 hasConceptScore W2805897895C2522767166 @default.
• W2805897895 hasConceptScore W2805897895C2780586882 @default.
• W2805897895 hasConceptScore W2805897895C33923547 @default.
• W2805897895 hasConceptScore W2805897895C36503486 @default.
• W2805897895 hasConceptScore W2805897895C41008148 @default.
• W2805897895 hasLocation W28058978951 @default.
• W2805897895 hasOpenAccess W2805897895 @default.
• W2805897895 hasPrimaryLocation W28058978951 @default.
• W2805897895 hasRelatedWork W1485749604 @default.
• W2805897895 hasRelatedWork W2803642672 @default.
• W2805897895 hasRelatedWork W2916797267 @default.
• W2805897895 hasRelatedWork W2920873626 @default.
• W2805897895 hasRelatedWork W2943285501 @default.
• W2805897895 hasRelatedWork W2949030303 @default.
• W2805897895 hasRelatedWork W2963226382 @default.
• W2805897895 hasRelatedWork W2963660754 @default.
• W2805897895 hasRelatedWork W2972918955 @default.
• W2805897895 hasRelatedWork W3035371891 @default.
• W2805897895 hasRelatedWork W3089371302 @default.

• next