Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912741785> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2912741785 abstract "As a nonlinear feature learning method, deep canonical correlation analysis (DCCA) has got a great success in computer vision. Compared with kernel methods, deep neural networks can more easily process large amounts of training data and do not require referring to the training set at test time. However, in the real world, due to the noise disturbance and the limited number of training samples, within-set and between-set sample covariance matrices cannot usually be estimated accurately, which causes that the gradient direction deviates from the true one when training DCCA. It incorporates fractional-order within-set and between-set scatter matrices to reduce the deviations of sample covariance matrices for gradient direction correction. In addition, to make full use of convolutional network’s feature extraction ability and fractional model in modifying neural network gradient directions, we further propose two novel convolutional network-based FDCCA methods, named convolutional neural network-based FDCCA (CNN-FDCCA) and two-convolutional neural networks based FDCCA (2CNNs-FDCCA), respectively. The experimental results on MNIST and RAVDNESS datasets show that FDCCA has better recognition rates than existing methods. The experiments on AT&T dataset show that CNN-FDCCA and 2CNNs-FDCCA have great robustness in processing images." @default.
- W2912741785 created "2019-02-21" @default.
- W2912741785 creator A5021293751 @default.
- W2912741785 creator A5032020402 @default.
- W2912741785 creator A5040159990 @default.
- W2912741785 creator A5055757510 @default.
- W2912741785 date "2019-01-01" @default.
- W2912741785 modified "2023-10-15" @default.
- W2912741785 title "A New Robust Deep Canonical Correlation Analysis Algorithm for Small Sample Problems" @default.
- W2912741785 doi "https://doi.org/10.1109/access.2019.2895363" @default.
- W2912741785 hasPublicationYear "2019" @default.
- W2912741785 type Work @default.
- W2912741785 sameAs 2912741785 @default.
- W2912741785 citedByCount "3" @default.
- W2912741785 countsByYear W29127417852020 @default.
- W2912741785 countsByYear W29127417852021 @default.
- W2912741785 countsByYear W29127417852022 @default.
- W2912741785 crossrefType "journal-article" @default.
- W2912741785 hasAuthorship W2912741785A5021293751 @default.
- W2912741785 hasAuthorship W2912741785A5032020402 @default.
- W2912741785 hasAuthorship W2912741785A5040159990 @default.
- W2912741785 hasAuthorship W2912741785A5055757510 @default.
- W2912741785 hasBestOaLocation W29127417851 @default.
- W2912741785 hasConcept C104317684 @default.
- W2912741785 hasConcept C105795698 @default.
- W2912741785 hasConcept C108583219 @default.
- W2912741785 hasConcept C11413529 @default.
- W2912741785 hasConcept C114614502 @default.
- W2912741785 hasConcept C153180895 @default.
- W2912741785 hasConcept C153874254 @default.
- W2912741785 hasConcept C154945302 @default.
- W2912741785 hasConcept C169903167 @default.
- W2912741785 hasConcept C178650346 @default.
- W2912741785 hasConcept C185142706 @default.
- W2912741785 hasConcept C185592680 @default.
- W2912741785 hasConcept C190502265 @default.
- W2912741785 hasConcept C33923547 @default.
- W2912741785 hasConcept C41008148 @default.
- W2912741785 hasConcept C50644808 @default.
- W2912741785 hasConcept C52622490 @default.
- W2912741785 hasConcept C55493867 @default.
- W2912741785 hasConcept C63479239 @default.
- W2912741785 hasConcept C74193536 @default.
- W2912741785 hasConcept C81363708 @default.
- W2912741785 hasConceptScore W2912741785C104317684 @default.
- W2912741785 hasConceptScore W2912741785C105795698 @default.
- W2912741785 hasConceptScore W2912741785C108583219 @default.
- W2912741785 hasConceptScore W2912741785C11413529 @default.
- W2912741785 hasConceptScore W2912741785C114614502 @default.
- W2912741785 hasConceptScore W2912741785C153180895 @default.
- W2912741785 hasConceptScore W2912741785C153874254 @default.
- W2912741785 hasConceptScore W2912741785C154945302 @default.
- W2912741785 hasConceptScore W2912741785C169903167 @default.
- W2912741785 hasConceptScore W2912741785C178650346 @default.
- W2912741785 hasConceptScore W2912741785C185142706 @default.
- W2912741785 hasConceptScore W2912741785C185592680 @default.
- W2912741785 hasConceptScore W2912741785C190502265 @default.
- W2912741785 hasConceptScore W2912741785C33923547 @default.
- W2912741785 hasConceptScore W2912741785C41008148 @default.
- W2912741785 hasConceptScore W2912741785C50644808 @default.
- W2912741785 hasConceptScore W2912741785C52622490 @default.
- W2912741785 hasConceptScore W2912741785C55493867 @default.
- W2912741785 hasConceptScore W2912741785C63479239 @default.
- W2912741785 hasConceptScore W2912741785C74193536 @default.
- W2912741785 hasConceptScore W2912741785C81363708 @default.
- W2912741785 hasFunder F4320321001 @default.
- W2912741785 hasFunder F4320324130 @default.
- W2912741785 hasLocation W29127417851 @default.
- W2912741785 hasOpenAccess W2912741785 @default.
- W2912741785 hasPrimaryLocation W29127417851 @default.
- W2912741785 hasRelatedWork W2335806594 @default.
- W2912741785 hasRelatedWork W2621864722 @default.
- W2912741785 hasRelatedWork W2732542196 @default.
- W2912741785 hasRelatedWork W2733060750 @default.
- W2912741785 hasRelatedWork W2773120646 @default.
- W2912741785 hasRelatedWork W2800691917 @default.
- W2912741785 hasRelatedWork W2807839383 @default.
- W2912741785 hasRelatedWork W2889587233 @default.
- W2912741785 hasRelatedWork W2901435809 @default.
- W2912741785 hasRelatedWork W4285816666 @default.
- W2912741785 isParatext "false" @default.
- W2912741785 isRetracted "false" @default.
- W2912741785 magId "2912741785" @default.
- W2912741785 workType "article" @default.