Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972188071> ?p ?o ?g. }
- W2972188071 endingPage "606" @default.
- W2972188071 startingPage "595" @default.
- W2972188071 abstract "Currently available uncertainty quantification (UQ) neural networks (NNs) are trained through the statistical error minimization. Therefore, NNs perform poorly for critical input patterns. Some input patterns have lower coverage probabilities than others. Such input dependent performance is evident in electricity price prediction where different input features are coming from heterogeneous monitoring sources. This paper proposes a prediction interval (PI) based UQ of the electricity price with the proposed partial adversarial training to achieve the input-domain independent performance. The proposed training consists of initial training, adversarial sample generations from critical samples and a final training with the combined datasets of critical samples and initial training samples. Critical situations are situations where prediction systems struggle to predict and make higher statistical errors. Multiple NNs are first trained with different initializations. Each uncovered sample to the NN pair in the training set generates an adversarial sample. The adversarial dataset is concatenated with the initial samples. The final NN training is performed with the combined dataset. The technique is visualized with rough sketches in both time and input domain. The feasibility and performance are examined on experimental electricity market price datasets." @default.
- W2972188071 created "2019-09-12" @default.
- W2972188071 creator A5013980122 @default.
- W2972188071 creator A5015293969 @default.
- W2972188071 creator A5059557438 @default.
- W2972188071 creator A5063766245 @default.
- W2972188071 date "2021-08-01" @default.
- W2972188071 modified "2023-09-27" @default.
- W2972188071 title "Partial Adversarial Training for Neural Network-Based Uncertainty Quantification" @default.
- W2972188071 cites W1966646381 @default.
- W2972188071 cites W1985505861 @default.
- W2972188071 cites W2016166216 @default.
- W2972188071 cites W2037634800 @default.
- W2972188071 cites W2056871913 @default.
- W2972188071 cites W2067796266 @default.
- W2972188071 cites W2074911163 @default.
- W2972188071 cites W2117462983 @default.
- W2972188071 cites W2155816288 @default.
- W2972188071 cites W2156604062 @default.
- W2972188071 cites W2339339993 @default.
- W2972188071 cites W2342990644 @default.
- W2972188071 cites W2411223467 @default.
- W2972188071 cites W2555546325 @default.
- W2972188071 cites W2559780401 @default.
- W2972188071 cites W2603766943 @default.
- W2972188071 cites W2689813587 @default.
- W2972188071 cites W2736385547 @default.
- W2972188071 cites W2742093080 @default.
- W2972188071 cites W2756290693 @default.
- W2972188071 cites W2757094782 @default.
- W2972188071 cites W2765939901 @default.
- W2972188071 cites W2807414627 @default.
- W2972188071 cites W2884414452 @default.
- W2972188071 cites W2885178111 @default.
- W2972188071 cites W2896203251 @default.
- W2972188071 cites W2896421845 @default.
- W2972188071 cites W2898512397 @default.
- W2972188071 cites W2899329456 @default.
- W2972188071 cites W2905363426 @default.
- W2972188071 cites W2911349806 @default.
- W2972188071 cites W2912614123 @default.
- W2972188071 cites W2914351560 @default.
- W2972188071 cites W2930586974 @default.
- W2972188071 cites W2942951085 @default.
- W2972188071 cites W2945958082 @default.
- W2972188071 cites W2962870214 @default.
- W2972188071 cites W4256248553 @default.
- W2972188071 doi "https://doi.org/10.1109/tetci.2019.2936546" @default.
- W2972188071 hasPublicationYear "2021" @default.
- W2972188071 type Work @default.
- W2972188071 sameAs 2972188071 @default.
- W2972188071 citedByCount "20" @default.
- W2972188071 countsByYear W29721880712019 @default.
- W2972188071 countsByYear W29721880712020 @default.
- W2972188071 countsByYear W29721880712021 @default.
- W2972188071 countsByYear W29721880712022 @default.
- W2972188071 countsByYear W29721880712023 @default.
- W2972188071 crossrefType "journal-article" @default.
- W2972188071 hasAuthorship W2972188071A5013980122 @default.
- W2972188071 hasAuthorship W2972188071A5015293969 @default.
- W2972188071 hasAuthorship W2972188071A5059557438 @default.
- W2972188071 hasAuthorship W2972188071A5063766245 @default.
- W2972188071 hasConcept C105795698 @default.
- W2972188071 hasConcept C119599485 @default.
- W2972188071 hasConcept C119857082 @default.
- W2972188071 hasConcept C121332964 @default.
- W2972188071 hasConcept C124101348 @default.
- W2972188071 hasConcept C127413603 @default.
- W2972188071 hasConcept C129848803 @default.
- W2972188071 hasConcept C134306372 @default.
- W2972188071 hasConcept C147764199 @default.
- W2972188071 hasConcept C153294291 @default.
- W2972188071 hasConcept C154945302 @default.
- W2972188071 hasConcept C177264268 @default.
- W2972188071 hasConcept C185592680 @default.
- W2972188071 hasConcept C198531522 @default.
- W2972188071 hasConcept C199360897 @default.
- W2972188071 hasConcept C206658404 @default.
- W2972188071 hasConcept C2777211547 @default.
- W2972188071 hasConcept C33923547 @default.
- W2972188071 hasConcept C36503486 @default.
- W2972188071 hasConcept C37736160 @default.
- W2972188071 hasConcept C41008148 @default.
- W2972188071 hasConcept C43617362 @default.
- W2972188071 hasConcept C50644808 @default.
- W2972188071 hasConceptScore W2972188071C105795698 @default.
- W2972188071 hasConceptScore W2972188071C119599485 @default.
- W2972188071 hasConceptScore W2972188071C119857082 @default.
- W2972188071 hasConceptScore W2972188071C121332964 @default.
- W2972188071 hasConceptScore W2972188071C124101348 @default.
- W2972188071 hasConceptScore W2972188071C127413603 @default.
- W2972188071 hasConceptScore W2972188071C129848803 @default.
- W2972188071 hasConceptScore W2972188071C134306372 @default.
- W2972188071 hasConceptScore W2972188071C147764199 @default.
- W2972188071 hasConceptScore W2972188071C153294291 @default.
- W2972188071 hasConceptScore W2972188071C154945302 @default.
- W2972188071 hasConceptScore W2972188071C177264268 @default.
- W2972188071 hasConceptScore W2972188071C185592680 @default.