Handling irregularly sampled signals with gated temporal convolutional networks

buir.contributor.authorAslan, Fatih
buir.contributor.authorKozat, S. Serdar
buir.contributor.orcidKozat, S. Serdar|0000-0002-6488-3848
dc.contributor.authorAslan, Fatih
dc.contributor.authorKozat, S. Serdar
dc.date.accessioned2023-02-22T08:18:16Z
dc.date.available2023-02-22T08:18:16Z
dc.date.issued2022-07-06
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe investigate the sequential modeling problem and introduce a novel gating mechanism into the temporal convolutional network architectures. In particular, we introduce the gated temporal convolutional network architecture with elaborately tailored gating mechanisms. In our implementation, we alter the way in which the gradients flow and avoid the vanishing or exploding gradient and the dead ReLU problems. The proposed GTCN architecture is able to model the irregularly sampled sequences as well. In our experiments, we show that the basic GTCN architecture is superior to the generic TCN architectures in various benchmark tasks requiring the modeling of long-term dependencies and irregular sampling intervals. Moreover, we achieve the state-of-the-art results on the permuted sequential MNIST and the sequential CIFAR10 benchmarks with the basic structure.en_US
dc.identifier.doi10.1007/s11760-022-02292-2en_US
dc.identifier.issn1863-1703
dc.identifier.urihttp://hdl.handle.net/11693/111600
dc.language.isoEnglishen_US
dc.relation.isversionofhttps://doi.org/10.1007/s11760-022-02292-2en_US
dc.source.titleSignal, Image and Video Processingen_US
dc.subjectIrregular samplingen_US
dc.subjectSequential learningen_US
dc.subjectTemporal convolutional networksen_US
dc.subjectTime series classificationen_US
dc.titleHandling irregularly sampled signals with gated temporal convolutional networksen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Handling_irregularly_sampled_signals_with_gated_temporal_convolutional_networks.pdf
Size:
400.58 KB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description: