Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912204606> ?p ?o ?g. }
- W2912204606 abstract "Abstract Background Deep neural networks have revolutionised machine learning, with unparalleled performance in object classification. However, in brain imaging (e.g. fMRI), the direct application of Convolutional Neural Networks (CNN) to decoding subject states or perception from imaging data seems impractical given the scarcity of available data. New method In this work we propose a robust method to transfer information from deep learning (DL) features to brain fMRI data with the goal of decoding. By adopting Reduced Rank Regression with Ridge Regularisation we establish a multivariate link between imaging data and the fully connected layer ( fc7 ) of a CNN. We exploit the reconstructed fc7 features by performing an object image classification task on two datasets: one of the largest fMRI databases, taken from different scanners from more than two hundred subjects watching different movie clips, and another with fMRI data taken while watching static images, Results The fc7 features could be significantly reconstructed from the imaging data, and led to significant decoding performance. Comparison with existing methods The decoding based on reconstructed fc7 outperformed the decoding based on imaging data alone. Conclusion In this work we show how to improve fMRI-based decoding benefiting from the mapping between functional data and CNN features. The potential advantage of the proposed method is twofold: the extraction of stimuli representations by means of an automatic procedure (unsupervised) and the embedding of high-dimensional neuroimaging data onto a space designed for visual object discrimination, leading to a more manageable space from dimensionality point of view." @default.
- W2912204606 created "2019-02-21" @default.
- W2912204606 creator A5004055341 @default.
- W2912204606 creator A5014976873 @default.
- W2912204606 creator A5020236644 @default.
- W2912204606 creator A5026206233 @default.
- W2912204606 creator A5052086841 @default.
- W2912204606 creator A5059231094 @default.
- W2912204606 creator A5063798638 @default.
- W2912204606 creator A5083404139 @default.
- W2912204606 creator A5085958018 @default.
- W2912204606 date "2019-02-03" @default.
- W2912204606 modified "2023-10-05" @default.
- W2912204606 title "Transfer learning of deep neural network representations for fMRI decoding" @default.
- W2912204606 cites W1655948089 @default.
- W2912204606 cites W1661793846 @default.
- W2912204606 cites W1715013381 @default.
- W2912204606 cites W1999563145 @default.
- W2912204606 cites W2003400098 @default.
- W2912204606 cites W2007226897 @default.
- W2912204606 cites W2016444985 @default.
- W2912204606 cites W2025341678 @default.
- W2912204606 cites W2040036684 @default.
- W2912204606 cites W2041788773 @default.
- W2912204606 cites W2047830667 @default.
- W2912204606 cites W2064863859 @default.
- W2912204606 cites W2072368990 @default.
- W2912204606 cites W2073309755 @default.
- W2912204606 cites W2090392676 @default.
- W2912204606 cites W2090739964 @default.
- W2912204606 cites W2101807845 @default.
- W2912204606 cites W2112180451 @default.
- W2912204606 cites W2113506774 @default.
- W2912204606 cites W2117539524 @default.
- W2912204606 cites W2119577735 @default.
- W2912204606 cites W2126810579 @default.
- W2912204606 cites W2136132248 @default.
- W2912204606 cites W2143110649 @default.
- W2912204606 cites W2153579905 @default.
- W2912204606 cites W2155479901 @default.
- W2912204606 cites W2158863190 @default.
- W2912204606 cites W2161976355 @default.
- W2912204606 cites W2166403493 @default.
- W2912204606 cites W2176287621 @default.
- W2912204606 cites W2274405424 @default.
- W2912204606 cites W2289369827 @default.
- W2912204606 cites W2344461865 @default.
- W2912204606 cites W2346674441 @default.
- W2912204606 cites W2412480261 @default.
- W2912204606 cites W2507706845 @default.
- W2912204606 cites W2537084945 @default.
- W2912204606 cites W2738724892 @default.
- W2912204606 cites W2756242344 @default.
- W2912204606 cites W2787184884 @default.
- W2912204606 cites W2789214634 @default.
- W2912204606 cites W2951793354 @default.
- W2912204606 cites W2962981304 @default.
- W2912204606 cites W2964304793 @default.
- W2912204606 cites W3102476541 @default.
- W2912204606 cites W3104767295 @default.
- W2912204606 cites W3209311252 @default.
- W2912204606 cites W4300009529 @default.
- W2912204606 cites W46718429 @default.
- W2912204606 doi "https://doi.org/10.1101/535377" @default.
- W2912204606 hasPublicationYear "2019" @default.
- W2912204606 type Work @default.
- W2912204606 sameAs 2912204606 @default.
- W2912204606 citedByCount "1" @default.
- W2912204606 countsByYear W29122046062020 @default.
- W2912204606 crossrefType "posted-content" @default.
- W2912204606 hasAuthorship W2912204606A5004055341 @default.
- W2912204606 hasAuthorship W2912204606A5014976873 @default.
- W2912204606 hasAuthorship W2912204606A5020236644 @default.
- W2912204606 hasAuthorship W2912204606A5026206233 @default.
- W2912204606 hasAuthorship W2912204606A5052086841 @default.
- W2912204606 hasAuthorship W2912204606A5059231094 @default.
- W2912204606 hasAuthorship W2912204606A5063798638 @default.
- W2912204606 hasAuthorship W2912204606A5083404139 @default.
- W2912204606 hasAuthorship W2912204606A5085958018 @default.
- W2912204606 hasBestOaLocation W29122046061 @default.
- W2912204606 hasConcept C101738243 @default.
- W2912204606 hasConcept C108583219 @default.
- W2912204606 hasConcept C118552586 @default.
- W2912204606 hasConcept C150899416 @default.
- W2912204606 hasConcept C153180895 @default.
- W2912204606 hasConcept C154945302 @default.
- W2912204606 hasConcept C15744967 @default.
- W2912204606 hasConcept C2781238097 @default.
- W2912204606 hasConcept C31972630 @default.
- W2912204606 hasConcept C40743351 @default.
- W2912204606 hasConcept C41008148 @default.
- W2912204606 hasConcept C57273362 @default.
- W2912204606 hasConcept C58693492 @default.
- W2912204606 hasConcept C76155785 @default.
- W2912204606 hasConcept C81363708 @default.
- W2912204606 hasConceptScore W2912204606C101738243 @default.
- W2912204606 hasConceptScore W2912204606C108583219 @default.
- W2912204606 hasConceptScore W2912204606C118552586 @default.
- W2912204606 hasConceptScore W2912204606C150899416 @default.
- W2912204606 hasConceptScore W2912204606C153180895 @default.