Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386558490> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4386558490 endingPage "429" @default.
- W4386558490 startingPage "429" @default.
- W4386558490 abstract "Bayesian neural networks (BNNs) are effective tools for a variety of tasks that allow for the estimation of the uncertainty of the model. As BNNs use prior constraints on parameters, they are better regularized and less prone to overfitting, which is a serious issue for brain–computer interfaces (BCIs), where typically only small training datasets are available. Here, we tested, on the BCI Competition IV 2a motor imagery dataset, if the performance of the widely used, effective neural network classifiers EEGNet and Shallow ConvNet can be improved by turning them into BNNs. Accuracy indeed was higher, at least for a BNN based on Shallow ConvNet with two of three tested prior distributions. We also assessed if BNN-based uncertainty estimation could be used as a tool for out-of-domain (OOD) data detection. The OOD detection worked well only in certain participants; however, we expect that further development of the method may make it work sufficiently well for practical applications." @default.
- W4386558490 created "2023-09-09" @default.
- W4386558490 creator A5009313402 @default.
- W4386558490 creator A5078766419 @default.
- W4386558490 creator A5092829575 @default.
- W4386558490 date "2023-09-08" @default.
- W4386558490 modified "2023-10-16" @default.
- W4386558490 title "Bayesian Opportunities for Brain–Computer Interfaces: Enhancement of the Existing Classification Algorithms and Out-of-Domain Detection" @default.
- W4386558490 cites W2011301426 @default.
- W4386558490 cites W2053933777 @default.
- W4386558490 cites W2133382750 @default.
- W4386558490 cites W2169918686 @default.
- W4386558490 cites W2346095864 @default.
- W4386558490 cites W2422365436 @default.
- W4386558490 cites W2475311545 @default.
- W4386558490 cites W2741907166 @default.
- W4386558490 cites W2794345050 @default.
- W4386558490 cites W2891642103 @default.
- W4386558490 cites W3014773921 @default.
- W4386558490 cites W3043426275 @default.
- W4386558490 cites W3091380357 @default.
- W4386558490 cites W3101380508 @default.
- W4386558490 cites W3102455230 @default.
- W4386558490 cites W3103145119 @default.
- W4386558490 cites W3103278764 @default.
- W4386558490 cites W3129458144 @default.
- W4386558490 cites W3150635270 @default.
- W4386558490 cites W3158982735 @default.
- W4386558490 cites W3175379388 @default.
- W4386558490 cites W3199755270 @default.
- W4386558490 cites W4313889970 @default.
- W4386558490 cites W4321607974 @default.
- W4386558490 cites W4385338410 @default.
- W4386558490 doi "https://doi.org/10.3390/a16090429" @default.
- W4386558490 hasPublicationYear "2023" @default.
- W4386558490 type Work @default.
- W4386558490 citedByCount "0" @default.
- W4386558490 crossrefType "journal-article" @default.
- W4386558490 hasAuthorship W4386558490A5009313402 @default.
- W4386558490 hasAuthorship W4386558490A5078766419 @default.
- W4386558490 hasAuthorship W4386558490A5092829575 @default.
- W4386558490 hasBestOaLocation W43865584901 @default.
- W4386558490 hasConcept C107673813 @default.
- W4386558490 hasConcept C118552586 @default.
- W4386558490 hasConcept C119857082 @default.
- W4386558490 hasConcept C134306372 @default.
- W4386558490 hasConcept C136197465 @default.
- W4386558490 hasConcept C154945302 @default.
- W4386558490 hasConcept C15744967 @default.
- W4386558490 hasConcept C173201364 @default.
- W4386558490 hasConcept C22019652 @default.
- W4386558490 hasConcept C33923547 @default.
- W4386558490 hasConcept C36503486 @default.
- W4386558490 hasConcept C41008148 @default.
- W4386558490 hasConcept C50644808 @default.
- W4386558490 hasConcept C522805319 @default.
- W4386558490 hasConcept C81363708 @default.
- W4386558490 hasConceptScore W4386558490C107673813 @default.
- W4386558490 hasConceptScore W4386558490C118552586 @default.
- W4386558490 hasConceptScore W4386558490C119857082 @default.
- W4386558490 hasConceptScore W4386558490C134306372 @default.
- W4386558490 hasConceptScore W4386558490C136197465 @default.
- W4386558490 hasConceptScore W4386558490C154945302 @default.
- W4386558490 hasConceptScore W4386558490C15744967 @default.
- W4386558490 hasConceptScore W4386558490C173201364 @default.
- W4386558490 hasConceptScore W4386558490C22019652 @default.
- W4386558490 hasConceptScore W4386558490C33923547 @default.
- W4386558490 hasConceptScore W4386558490C36503486 @default.
- W4386558490 hasConceptScore W4386558490C41008148 @default.
- W4386558490 hasConceptScore W4386558490C50644808 @default.
- W4386558490 hasConceptScore W4386558490C522805319 @default.
- W4386558490 hasConceptScore W4386558490C81363708 @default.
- W4386558490 hasFunder F4320324099 @default.
- W4386558490 hasIssue "9" @default.
- W4386558490 hasLocation W43865584901 @default.
- W4386558490 hasOpenAccess W4386558490 @default.
- W4386558490 hasPrimaryLocation W43865584901 @default.
- W4386558490 hasRelatedWork W2725603402 @default.
- W4386558490 hasRelatedWork W2767651786 @default.
- W4386558490 hasRelatedWork W2917517086 @default.
- W4386558490 hasRelatedWork W2989932438 @default.
- W4386558490 hasRelatedWork W3012393889 @default.
- W4386558490 hasRelatedWork W3081496756 @default.
- W4386558490 hasRelatedWork W3099765033 @default.
- W4386558490 hasRelatedWork W3127819136 @default.
- W4386558490 hasRelatedWork W4210794429 @default.
- W4386558490 hasRelatedWork W4220996320 @default.
- W4386558490 hasVolume "16" @default.
- W4386558490 isParatext "false" @default.
- W4386558490 isRetracted "false" @default.
- W4386558490 workType "article" @default.