Matches in SemOpenAlex for { <https://semopenalex.org/work/W2601938104> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2601938104 abstract "Deep learning with convolutional neural networks (deep ConvNets) hasrevolutionized computer vision through end-to-end learning, i.e. learning fromthe raw data. Now, there is increasing interest in using deep ConvNets forend-to-end EEG analysis. However, little is known about many important aspectsof how to design and train ConvNets for end-to-end EEG decoding, and there isstill a lack of techniques to visualize the informative EEG features theConvNets learn. Here, we studied deep ConvNets with a range of different architectures,designed for decoding imagined or executed movements from raw EEG. Our resultsshow that recent advances from the machine learning field, including batchnormalization and exponential linear units, together with a cropped trainingstrategy, boosted the deep ConvNets decoding performance, reaching orsurpassing that of the widely-used filter bank common spatial patterns (FBCSP)decoding algorithm. While FBCSP is designed to use spectral power modulations,the features used by ConvNets are not fixed a priori. Our novel methods forvisualizing the learned features demonstrated that ConvNets indeed learned touse spectral power modulations in the alpha, beta and high gamma frequencies.These methods also proved useful as a technique for spatially mapping thelearned features, revealing the topography of the causal contributions offeatures in different frequency bands to decoding the movement classes. Our study thus shows how to design and train ConvNets to decodemovement-related information from the raw EEG without handcrafted features andhighlights the potential of deep ConvNets combined with advanced visualizationtechniques for EEG-based brain mapping." @default.
- W2601938104 created "2017-04-07" @default.
- W2601938104 creator A5016872527 @default.
- W2601938104 creator A5017985443 @default.
- W2601938104 creator A5018131113 @default.
- W2601938104 creator A5031002895 @default.
- W2601938104 creator A5049330818 @default.
- W2601938104 creator A5054081898 @default.
- W2601938104 creator A5067573169 @default.
- W2601938104 creator A5081813991 @default.
- W2601938104 creator A5084499878 @default.
- W2601938104 date "2017-03-15" @default.
- W2601938104 modified "2023-09-27" @default.
- W2601938104 title "Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG." @default.
- W2601938104 hasPublicationYear "2017" @default.
- W2601938104 type Work @default.
- W2601938104 sameAs 2601938104 @default.
- W2601938104 citedByCount "18" @default.
- W2601938104 countsByYear W26019381042017 @default.
- W2601938104 countsByYear W26019381042018 @default.
- W2601938104 countsByYear W26019381042019 @default.
- W2601938104 countsByYear W26019381042020 @default.
- W2601938104 countsByYear W26019381042021 @default.
- W2601938104 crossrefType "posted-content" @default.
- W2601938104 hasAuthorship W2601938104A5016872527 @default.
- W2601938104 hasAuthorship W2601938104A5017985443 @default.
- W2601938104 hasAuthorship W2601938104A5018131113 @default.
- W2601938104 hasAuthorship W2601938104A5031002895 @default.
- W2601938104 hasAuthorship W2601938104A5049330818 @default.
- W2601938104 hasAuthorship W2601938104A5054081898 @default.
- W2601938104 hasAuthorship W2601938104A5067573169 @default.
- W2601938104 hasAuthorship W2601938104A5081813991 @default.
- W2601938104 hasAuthorship W2601938104A5084499878 @default.
- W2601938104 hasConcept C108583219 @default.
- W2601938104 hasConcept C11413529 @default.
- W2601938104 hasConcept C118552586 @default.
- W2601938104 hasConcept C119857082 @default.
- W2601938104 hasConcept C136886441 @default.
- W2601938104 hasConcept C144024400 @default.
- W2601938104 hasConcept C153180895 @default.
- W2601938104 hasConcept C154945302 @default.
- W2601938104 hasConcept C15744967 @default.
- W2601938104 hasConcept C173201364 @default.
- W2601938104 hasConcept C19165224 @default.
- W2601938104 hasConcept C36464697 @default.
- W2601938104 hasConcept C41008148 @default.
- W2601938104 hasConcept C522805319 @default.
- W2601938104 hasConcept C54808283 @default.
- W2601938104 hasConcept C57273362 @default.
- W2601938104 hasConcept C81363708 @default.
- W2601938104 hasConceptScore W2601938104C108583219 @default.
- W2601938104 hasConceptScore W2601938104C11413529 @default.
- W2601938104 hasConceptScore W2601938104C118552586 @default.
- W2601938104 hasConceptScore W2601938104C119857082 @default.
- W2601938104 hasConceptScore W2601938104C136886441 @default.
- W2601938104 hasConceptScore W2601938104C144024400 @default.
- W2601938104 hasConceptScore W2601938104C153180895 @default.
- W2601938104 hasConceptScore W2601938104C154945302 @default.
- W2601938104 hasConceptScore W2601938104C15744967 @default.
- W2601938104 hasConceptScore W2601938104C173201364 @default.
- W2601938104 hasConceptScore W2601938104C19165224 @default.
- W2601938104 hasConceptScore W2601938104C36464697 @default.
- W2601938104 hasConceptScore W2601938104C41008148 @default.
- W2601938104 hasConceptScore W2601938104C522805319 @default.
- W2601938104 hasConceptScore W2601938104C54808283 @default.
- W2601938104 hasConceptScore W2601938104C57273362 @default.
- W2601938104 hasConceptScore W2601938104C81363708 @default.
- W2601938104 hasLocation W26019381041 @default.
- W2601938104 hasOpenAccess W2601938104 @default.
- W2601938104 hasPrimaryLocation W26019381041 @default.
- W2601938104 hasRelatedWork W1522301498 @default.
- W2601938104 hasRelatedWork W1686810756 @default.
- W2601938104 hasRelatedWork W2150590430 @default.
- W2601938104 hasRelatedWork W2163605009 @default.
- W2601938104 hasRelatedWork W2176412452 @default.
- W2601938104 hasRelatedWork W2741907166 @default.
- W2601938104 hasRelatedWork W2768578923 @default.
- W2601938104 hasRelatedWork W2913246999 @default.
- W2601938104 hasRelatedWork W2919115771 @default.
- W2601938104 hasRelatedWork W2921618710 @default.
- W2601938104 hasRelatedWork W2949117887 @default.
- W2601938104 hasRelatedWork W2961390542 @default.
- W2601938104 hasRelatedWork W2962699674 @default.
- W2601938104 hasRelatedWork W2963355311 @default.
- W2601938104 hasRelatedWork W2966010920 @default.
- W2601938104 hasRelatedWork W2990809856 @default.
- W2601938104 hasRelatedWork W3040822952 @default.
- W2601938104 hasRelatedWork W3102455230 @default.
- W2601938104 hasRelatedWork W3105605673 @default.
- W2601938104 hasRelatedWork W3113058752 @default.
- W2601938104 isParatext "false" @default.
- W2601938104 isRetracted "false" @default.
- W2601938104 magId "2601938104" @default.
- W2601938104 workType "article" @default.