FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113568521> ?p ?o ?g. }

• W3113568521 endingPage "7822" @default.
• W3113568521 startingPage "7815" @default.
• W3113568521 abstract "Traditional deep neural networks (NNs) have significantly contributed to the state-of-the-art performance in the task of classification under various application domains. However, NNs have not considered inherent uncertainty in data associated with the class probabilities where misclassification under uncertainty may easily introduce high risk in decision making in real-world contexts (e.g., misclassification of objects in roads leads to serious accidents). Unlike Bayesian NN that indirectly infer uncertainty through weight uncertainties, evidential NNs (ENNs) have been recently proposed to explicitly model the uncertainty of class probabilities and use them for classification tasks. An ENN offers the formulation of the predictions of NNs as subjective opinions and learns the function by collecting an amount of evidence that can form the subjective opinions by a deterministic NN from data. However, the ENN is trained as a black box without explicitly considering inherent uncertainty in data with their different root causes, such as vacuity (i.e., uncertainty due to a lack of evidence) or dissonance (i.e., uncertainty due to conflicting evidence). By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem. We took a hybrid approach that combines Wasserstein Generative Adversarial Network (WGAN) with ENNs to jointly train a model with prior knowledge of a certain class, which has high vacuity for OOD samples. Via extensive empirical experiments based on both synthetic and real-world datasets, we demonstrated that the estimation of uncertainty by WENN can significantly help distinguish OOD samples from boundary samples. WENN outperformed in OOD detection when compared with other competitive counterparts." @default.
• W3113568521 created "2021-01-05" @default.
• W3113568521 creator A5011649304 @default.
• W3113568521 creator A5036221931 @default.
• W3113568521 creator A5074473139 @default.
• W3113568521 creator A5083563688 @default.
• W3113568521 creator A5090876899 @default.
• W3113568521 date "2021-05-18" @default.
• W3113568521 modified "2023-09-30" @default.
• W3113568521 title "Multidimensional Uncertainty-Aware Evidential Neural Networks" @default.
• W3113568521 cites W1686810756 @default.
• W3113568521 cites W1995875735 @default.
• W3113568521 cites W2099471712 @default.
• W3113568521 cites W2112796928 @default.
• W3113568521 cites W2145607950 @default.
• W3113568521 cites W2194775991 @default.
• W3113568521 cites W2335728318 @default.
• W3113568521 cites W2592505114 @default.
• W3113568521 cites W2750384547 @default.
• W3113568521 cites W2767414122 @default.
• W3113568521 cites W2767449908 @default.
• W3113568521 cites W2768927604 @default.
• W3113568521 cites W2788907134 @default.
• W3113568521 cites W2806471870 @default.
• W3113568521 cites W2892237532 @default.
• W3113568521 cites W2904981516 @default.
• W3113568521 cites W2950517871 @default.
• W3113568521 cites W2951266961 @default.
• W3113568521 cites W2952053192 @default.
• W3113568521 cites W2962879692 @default.
• W3113568521 cites W2963207607 @default.
• W3113568521 cites W2963238274 @default.
• W3113568521 cites W2963995504 @default.
• W3113568521 cites W2964059111 @default.
• W3113568521 cites W2980876340 @default.
• W3113568521 cites W2995488598 @default.
• W3113568521 cites W3033207542 @default.
• W3113568521 cites W3118608800 @default.
• W3113568521 cites W598128971 @default.
• W3113568521 cites W967544008 @default.
• W3113568521 doi "https://doi.org/10.1609/aaai.v35i9.16954" @default.
• W3113568521 hasPublicationYear "2021" @default.
• W3113568521 type Work @default.
• W3113568521 sameAs 3113568521 @default.
• W3113568521 citedByCount "2" @default.
• W3113568521 countsByYear W31135685212023 @default.
• W3113568521 crossrefType "journal-article" @default.
• W3113568521 hasAuthorship W3113568521A5011649304 @default.
• W3113568521 hasAuthorship W3113568521A5036221931 @default.
• W3113568521 hasAuthorship W3113568521A5074473139 @default.
• W3113568521 hasAuthorship W3113568521A5083563688 @default.
• W3113568521 hasAuthorship W3113568521A5090876899 @default.
• W3113568521 hasBestOaLocation W31135685211 @default.
• W3113568521 hasConcept C107673813 @default.
• W3113568521 hasConcept C119857082 @default.
• W3113568521 hasConcept C124101348 @default.
• W3113568521 hasConcept C14036430 @default.
• W3113568521 hasConcept C154945302 @default.
• W3113568521 hasConcept C162324750 @default.
• W3113568521 hasConcept C187736073 @default.
• W3113568521 hasConcept C2777212361 @default.
• W3113568521 hasConcept C2780451532 @default.
• W3113568521 hasConcept C33724603 @default.
• W3113568521 hasConcept C41008148 @default.
• W3113568521 hasConcept C50644808 @default.
• W3113568521 hasConcept C78458016 @default.
• W3113568521 hasConcept C86803240 @default.
• W3113568521 hasConceptScore W3113568521C107673813 @default.
• W3113568521 hasConceptScore W3113568521C119857082 @default.
• W3113568521 hasConceptScore W3113568521C124101348 @default.
• W3113568521 hasConceptScore W3113568521C14036430 @default.
• W3113568521 hasConceptScore W3113568521C154945302 @default.
• W3113568521 hasConceptScore W3113568521C162324750 @default.
• W3113568521 hasConceptScore W3113568521C187736073 @default.
• W3113568521 hasConceptScore W3113568521C2777212361 @default.
• W3113568521 hasConceptScore W3113568521C2780451532 @default.
• W3113568521 hasConceptScore W3113568521C33724603 @default.
• W3113568521 hasConceptScore W3113568521C41008148 @default.
• W3113568521 hasConceptScore W3113568521C50644808 @default.
• W3113568521 hasConceptScore W3113568521C78458016 @default.
• W3113568521 hasConceptScore W3113568521C86803240 @default.
• W3113568521 hasIssue "9" @default.
• W3113568521 hasLocation W31135685211 @default.
• W3113568521 hasLocation W31135685212 @default.
• W3113568521 hasOpenAccess W3113568521 @default.
• W3113568521 hasPrimaryLocation W31135685211 @default.
• W3113568521 hasRelatedWork W2081647779 @default.
• W3113568521 hasRelatedWork W2961085424 @default.
• W3113568521 hasRelatedWork W3046775127 @default.
• W3113568521 hasRelatedWork W3170094116 @default.
• W3113568521 hasRelatedWork W4285260836 @default.
• W3113568521 hasRelatedWork W4286629047 @default.
• W3113568521 hasRelatedWork W4306321456 @default.
• W3113568521 hasRelatedWork W4306674287 @default.
• W3113568521 hasRelatedWork W4385957992 @default.
• W3113568521 hasRelatedWork W4224009465 @default.
• W3113568521 hasVolume "35" @default.
• W3113568521 isParatext "false" @default.

• next