Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176622755> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3176622755 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.
- W3176622755 created "2021-07-05" @default.
- W3176622755 creator A5011649304 @default.
- W3176622755 creator A5021979312 @default.
- W3176622755 creator A5036221931 @default.
- W3176622755 creator A5074473139 @default.
- W3176622755 creator A5090876899 @default.
- W3176622755 date "2020-12-25" @default.
- W3176622755 modified "2023-09-26" @default.
- W3176622755 title "Multidimensional Uncertainty-Aware Evidential Neural Networks" @default.
- W3176622755 doi "https://doi.org/10.48550/arxiv.2012.13676" @default.
- W3176622755 hasPublicationYear "2020" @default.
- W3176622755 type Work @default.
- W3176622755 sameAs 3176622755 @default.
- W3176622755 citedByCount "0" @default.
- W3176622755 crossrefType "posted-content" @default.
- W3176622755 hasAuthorship W3176622755A5011649304 @default.
- W3176622755 hasAuthorship W3176622755A5021979312 @default.
- W3176622755 hasAuthorship W3176622755A5036221931 @default.
- W3176622755 hasAuthorship W3176622755A5074473139 @default.
- W3176622755 hasAuthorship W3176622755A5090876899 @default.
- W3176622755 hasBestOaLocation W31766227551 @default.
- W3176622755 hasConcept C107673813 @default.
- W3176622755 hasConcept C119857082 @default.
- W3176622755 hasConcept C124101348 @default.
- W3176622755 hasConcept C14036430 @default.
- W3176622755 hasConcept C154945302 @default.
- W3176622755 hasConcept C162324750 @default.
- W3176622755 hasConcept C187736073 @default.
- W3176622755 hasConcept C2777212361 @default.
- W3176622755 hasConcept C2780451532 @default.
- W3176622755 hasConcept C33724603 @default.
- W3176622755 hasConcept C41008148 @default.
- W3176622755 hasConcept C50644808 @default.
- W3176622755 hasConcept C78458016 @default.
- W3176622755 hasConcept C86803240 @default.
- W3176622755 hasConceptScore W3176622755C107673813 @default.
- W3176622755 hasConceptScore W3176622755C119857082 @default.
- W3176622755 hasConceptScore W3176622755C124101348 @default.
- W3176622755 hasConceptScore W3176622755C14036430 @default.
- W3176622755 hasConceptScore W3176622755C154945302 @default.
- W3176622755 hasConceptScore W3176622755C162324750 @default.
- W3176622755 hasConceptScore W3176622755C187736073 @default.
- W3176622755 hasConceptScore W3176622755C2777212361 @default.
- W3176622755 hasConceptScore W3176622755C2780451532 @default.
- W3176622755 hasConceptScore W3176622755C33724603 @default.
- W3176622755 hasConceptScore W3176622755C41008148 @default.
- W3176622755 hasConceptScore W3176622755C50644808 @default.
- W3176622755 hasConceptScore W3176622755C78458016 @default.
- W3176622755 hasConceptScore W3176622755C86803240 @default.
- W3176622755 hasLocation W31766227551 @default.
- W3176622755 hasOpenAccess W3176622755 @default.
- W3176622755 hasPrimaryLocation W31766227551 @default.
- W3176622755 hasRelatedWork W1956930971 @default.
- W3176622755 hasRelatedWork W1969165474 @default.
- W3176622755 hasRelatedWork W2152579687 @default.
- W3176622755 hasRelatedWork W2902946190 @default.
- W3176622755 hasRelatedWork W2911666059 @default.
- W3176622755 hasRelatedWork W3045385837 @default.
- W3176622755 hasRelatedWork W3154094704 @default.
- W3176622755 hasRelatedWork W32248825 @default.
- W3176622755 hasRelatedWork W96862169 @default.
- W3176622755 hasRelatedWork W1629725936 @default.
- W3176622755 isParatext "false" @default.
- W3176622755 isRetracted "false" @default.
- W3176622755 magId "3176622755" @default.
- W3176622755 workType "article" @default.