FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204005071> ?p ?o ?g. }

• W3204005071 abstract "Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment. Sequential and parallel ensemble techniques have shown improved performance of ML systems in multi-modal settings by leveraging the feature sets together. We propose an uncertainty-aware boosting technique for multi-modal ensembling in order to focus on the data points with higher associated uncertainty estimates, rather than the ones with higher loss values. We evaluate this method on healthcare tasks related to Dementia and Parkinson's disease which involve real-world multi-modal speech and text data, wherein our method shows an improved performance. Additional analysis suggests that introducing uncertainty-awareness into the boosted ensembles decreases the overall entropy of the system, making it more robust to heteroscedasticity in the data, as well as better calibrating each of the modalities along with high quality prediction intervals. We open-source our entire codebase at https://github.com/usarawgi911//Uncertainty-aware-boosting." @default.
• W3204005071 created "2021-10-11" @default.
• W3204005071 creator A5009567492 @default.
• W3204005071 creator A5016137147 @default.
• W3204005071 creator A5047589197 @default.
• W3204005071 creator A5064740850 @default.
• W3204005071 creator A5081457786 @default.
• W3204005071 date "2021-07-18" @default.
• W3204005071 modified "2023-10-02" @default.
• W3204005071 title "Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings" @default.
• W3204005071 cites W1678356000 @default.
• W3204005071 cites W1719489212 @default.
• W3204005071 cites W1929216574 @default.
• W3204005071 cites W1988790447 @default.
• W3204005071 cites W2009803366 @default.
• W3204005071 cites W2085662862 @default.
• W3204005071 cites W2090777335 @default.
• W3204005071 cites W2095898861 @default.
• W3204005071 cites W2108677974 @default.
• W3204005071 cites W2109140840 @default.
• W3204005071 cites W2110398209 @default.
• W3204005071 cites W2111051539 @default.
• W3204005071 cites W2154029067 @default.
• W3204005071 cites W2164411961 @default.
• W3204005071 cites W2167433878 @default.
• W3204005071 cites W2248139833 @default.
• W3204005071 cites W2293638506 @default.
• W3204005071 cites W2462906003 @default.
• W3204005071 cites W2600383743 @default.
• W3204005071 cites W2619383789 @default.
• W3204005071 cites W2899778597 @default.
• W3204005071 cites W2907020378 @default.
• W3204005071 cites W2912934387 @default.
• W3204005071 cites W2919115771 @default.
• W3204005071 cites W2946361733 @default.
• W3204005071 cites W2951595529 @default.
• W3204005071 cites W2962689739 @default.
• W3204005071 cites W2962995943 @default.
• W3204005071 cites W2963238274 @default.
• W3204005071 cites W2963476860 @default.
• W3204005071 cites W2963677766 @default.
• W3204005071 cites W2964052793 @default.
• W3204005071 cites W2964059111 @default.
• W3204005071 cites W2964212410 @default.
• W3204005071 cites W2966294393 @default.
• W3204005071 cites W2970859221 @default.
• W3204005071 cites W2990037398 @default.
• W3204005071 cites W2995333506 @default.
• W3204005071 cites W2997129641 @default.
• W3204005071 cites W2998618342 @default.
• W3204005071 cites W3018928030 @default.
• W3204005071 cites W3030648110 @default.
• W3204005071 cites W3035562930 @default.
• W3204005071 cites W3037939899 @default.
• W3204005071 cites W3088909055 @default.
• W3204005071 cites W3094909210 @default.
• W3204005071 cites W3095395418 @default.
• W3204005071 cites W3095738426 @default.
• W3204005071 cites W3096912371 @default.
• W3204005071 cites W3097109903 @default.
• W3204005071 cites W3097288651 @default.
• W3204005071 cites W3099111334 @default.
• W3204005071 cites W3100511085 @default.
• W3204005071 cites W3102476541 @default.
• W3204005071 cites W3131571384 @default.
• W3204005071 cites W2108719358 @default.
• W3204005071 doi "https://doi.org/10.1109/ijcnn52387.2021.9534161" @default.
• W3204005071 hasPublicationYear "2021" @default.
• W3204005071 type Work @default.
• W3204005071 sameAs 3204005071 @default.
• W3204005071 citedByCount "1" @default.
• W3204005071 countsByYear W32040050712023 @default.
• W3204005071 crossrefType "proceedings-article" @default.
• W3204005071 hasAuthorship W3204005071A5009567492 @default.
• W3204005071 hasAuthorship W3204005071A5016137147 @default.
• W3204005071 hasAuthorship W3204005071A5047589197 @default.
• W3204005071 hasAuthorship W3204005071A5064740850 @default.
• W3204005071 hasAuthorship W3204005071A5081457786 @default.
• W3204005071 hasBestOaLocation W32040050712 @default.
• W3204005071 hasConcept C106301342 @default.
• W3204005071 hasConcept C119857082 @default.
• W3204005071 hasConcept C121332964 @default.
• W3204005071 hasConcept C124101348 @default.
• W3204005071 hasConcept C154945302 @default.
• W3204005071 hasConcept C15744967 @default.
• W3204005071 hasConcept C185592680 @default.
• W3204005071 hasConcept C188027245 @default.
• W3204005071 hasConcept C41008148 @default.
• W3204005071 hasConcept C46686674 @default.
• W3204005071 hasConcept C51110983 @default.
• W3204005071 hasConcept C62520636 @default.
• W3204005071 hasConcept C71139939 @default.
• W3204005071 hasConcept C77805123 @default.
• W3204005071 hasConceptScore W3204005071C106301342 @default.
• W3204005071 hasConceptScore W3204005071C119857082 @default.
• W3204005071 hasConceptScore W3204005071C121332964 @default.
• W3204005071 hasConceptScore W3204005071C124101348 @default.
• W3204005071 hasConceptScore W3204005071C154945302 @default.
• W3204005071 hasConceptScore W3204005071C15744967 @default.
• W3204005071 hasConceptScore W3204005071C185592680 @default.

• next