Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204153914> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3204153914 abstract "We introduce four principles for explainable artificial intelligence (AI) that comprise fundamental properties for explainable AI systems. We propose that explainable AI systems deliver accompanying evidence or reasons for outcomes and processes; provide explanations that are understandable to individual users; provide explanations that correctly reflect the system s process for generating the output; and that a system only operates under conditions for which it was designed and when it reaches sufficient confidence in its output. We have termed these four principles as explanation, meaningful, explanation accuracy, and knowledge limits, respectively. Through significant stakeholder engagement, these four principles were developed to encompass the multidisciplinary nature of explainable AI, including the fields of computer science, engineering, and psychology. Because one-sizefits-all explanations do not exist, different users will require different types of explanations. We present five categories of explanation and summarize theories of explainable AI. We give an overview of the algorithms in the field that cover the major classes of explainable algorithms. As a baseline comparison, we assess how well explanations provided by people follow our four principles. This assessment provides insights to the challenges of designing explainable AI systems." @default.
- W3204153914 created "2021-10-11" @default.
- W3204153914 creator A5019784062 @default.
- W3204153914 creator A5038103084 @default.
- W3204153914 creator A5039132893 @default.
- W3204153914 creator A5047918353 @default.
- W3204153914 creator A5061045207 @default.
- W3204153914 creator A5073231714 @default.
- W3204153914 creator A5073638056 @default.
- W3204153914 date "2021-09-29" @default.
- W3204153914 modified "2023-10-16" @default.
- W3204153914 title "Four principles of explainable artificial intelligence" @default.
- W3204153914 doi "https://doi.org/10.6028/nist.ir.8312" @default.
- W3204153914 hasPublicationYear "2021" @default.
- W3204153914 type Work @default.
- W3204153914 sameAs 3204153914 @default.
- W3204153914 citedByCount "31" @default.
- W3204153914 countsByYear W32041539142021 @default.
- W3204153914 countsByYear W32041539142022 @default.
- W3204153914 countsByYear W32041539142023 @default.
- W3204153914 crossrefType "report" @default.
- W3204153914 hasAuthorship W3204153914A5019784062 @default.
- W3204153914 hasAuthorship W3204153914A5038103084 @default.
- W3204153914 hasAuthorship W3204153914A5039132893 @default.
- W3204153914 hasAuthorship W3204153914A5047918353 @default.
- W3204153914 hasAuthorship W3204153914A5061045207 @default.
- W3204153914 hasAuthorship W3204153914A5073231714 @default.
- W3204153914 hasAuthorship W3204153914A5073638056 @default.
- W3204153914 hasBestOaLocation W32041539141 @default.
- W3204153914 hasConcept C111368507 @default.
- W3204153914 hasConcept C111919701 @default.
- W3204153914 hasConcept C12725497 @default.
- W3204153914 hasConcept C127313418 @default.
- W3204153914 hasConcept C127413603 @default.
- W3204153914 hasConcept C144024400 @default.
- W3204153914 hasConcept C154945302 @default.
- W3204153914 hasConcept C202444582 @default.
- W3204153914 hasConcept C22467394 @default.
- W3204153914 hasConcept C2522767166 @default.
- W3204153914 hasConcept C2780428219 @default.
- W3204153914 hasConcept C33923547 @default.
- W3204153914 hasConcept C36289849 @default.
- W3204153914 hasConcept C41008148 @default.
- W3204153914 hasConcept C539667460 @default.
- W3204153914 hasConcept C78519656 @default.
- W3204153914 hasConcept C9652623 @default.
- W3204153914 hasConcept C98045186 @default.
- W3204153914 hasConceptScore W3204153914C111368507 @default.
- W3204153914 hasConceptScore W3204153914C111919701 @default.
- W3204153914 hasConceptScore W3204153914C12725497 @default.
- W3204153914 hasConceptScore W3204153914C127313418 @default.
- W3204153914 hasConceptScore W3204153914C127413603 @default.
- W3204153914 hasConceptScore W3204153914C144024400 @default.
- W3204153914 hasConceptScore W3204153914C154945302 @default.
- W3204153914 hasConceptScore W3204153914C202444582 @default.
- W3204153914 hasConceptScore W3204153914C22467394 @default.
- W3204153914 hasConceptScore W3204153914C2522767166 @default.
- W3204153914 hasConceptScore W3204153914C2780428219 @default.
- W3204153914 hasConceptScore W3204153914C33923547 @default.
- W3204153914 hasConceptScore W3204153914C36289849 @default.
- W3204153914 hasConceptScore W3204153914C41008148 @default.
- W3204153914 hasConceptScore W3204153914C539667460 @default.
- W3204153914 hasConceptScore W3204153914C78519656 @default.
- W3204153914 hasConceptScore W3204153914C9652623 @default.
- W3204153914 hasConceptScore W3204153914C98045186 @default.
- W3204153914 hasFunder F4320332178 @default.
- W3204153914 hasLocation W32041539141 @default.
- W3204153914 hasLocation W32041539142 @default.
- W3204153914 hasOpenAccess W3204153914 @default.
- W3204153914 hasPrimaryLocation W32041539141 @default.
- W3204153914 hasRelatedWork W2005801347 @default.
- W3204153914 hasRelatedWork W2044536215 @default.
- W3204153914 hasRelatedWork W2186640231 @default.
- W3204153914 hasRelatedWork W2352448290 @default.
- W3204153914 hasRelatedWork W2365952365 @default.
- W3204153914 hasRelatedWork W2372385138 @default.
- W3204153914 hasRelatedWork W2380820513 @default.
- W3204153914 hasRelatedWork W2383111961 @default.
- W3204153914 hasRelatedWork W4286508873 @default.
- W3204153914 hasRelatedWork W4296359239 @default.
- W3204153914 isParatext "false" @default.
- W3204153914 isRetracted "false" @default.
- W3204153914 magId "3204153914" @default.
- W3204153914 workType "report" @default.