Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907770449> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2907770449 abstract "Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to inherent parallelism. However, currently there remains a performance gap to more expressive stochastic RNN variants, especially those with several layers of dependent random variables. In this work, we propose stochastic temporal convolutional networks (STCNs), a novel architecture that combines the computational advantages of temporal convolutional networks (TCN) with the representational power and robustness of stochastic latent spaces. In particular, we propose a hierarchy of stochastic latent variables that captures temporal dependencies at different time-scales. The architecture is modular and flexible due to the decoupling of the deterministic and stochastic layers. We show that the proposed architecture achieves state of the art log-likelihoods across several tasks. Finally, the model is capable of predicting high-quality synthetic samples over a long-range temporal horizon in modeling of handwritten text." @default.
- W2907770449 created "2019-01-11" @default.
- W2907770449 creator A5044027671 @default.
- W2907770449 creator A5052990107 @default.
- W2907770449 date "2019-05-01" @default.
- W2907770449 modified "2023-09-27" @default.
- W2907770449 title "STCN: Stochastic Temporal Convolutional Networks." @default.
- W2907770449 doi "https://doi.org/10.3929/ethz-b-000384546" @default.
- W2907770449 hasPublicationYear "2019" @default.
- W2907770449 type Work @default.
- W2907770449 sameAs 2907770449 @default.
- W2907770449 citedByCount "5" @default.
- W2907770449 countsByYear W29077704492019 @default.
- W2907770449 countsByYear W29077704492020 @default.
- W2907770449 countsByYear W29077704492021 @default.
- W2907770449 crossrefType "proceedings-article" @default.
- W2907770449 hasAuthorship W2907770449A5044027671 @default.
- W2907770449 hasAuthorship W2907770449A5052990107 @default.
- W2907770449 hasConcept C101468663 @default.
- W2907770449 hasConcept C104317684 @default.
- W2907770449 hasConcept C105795698 @default.
- W2907770449 hasConcept C111919701 @default.
- W2907770449 hasConcept C127491075 @default.
- W2907770449 hasConcept C147168706 @default.
- W2907770449 hasConcept C154945302 @default.
- W2907770449 hasConcept C185592680 @default.
- W2907770449 hasConcept C33923547 @default.
- W2907770449 hasConcept C41008148 @default.
- W2907770449 hasConcept C50644808 @default.
- W2907770449 hasConcept C55493867 @default.
- W2907770449 hasConcept C63479239 @default.
- W2907770449 hasConcept C80444323 @default.
- W2907770449 hasConcept C81363708 @default.
- W2907770449 hasConcept C8272713 @default.
- W2907770449 hasConceptScore W2907770449C101468663 @default.
- W2907770449 hasConceptScore W2907770449C104317684 @default.
- W2907770449 hasConceptScore W2907770449C105795698 @default.
- W2907770449 hasConceptScore W2907770449C111919701 @default.
- W2907770449 hasConceptScore W2907770449C127491075 @default.
- W2907770449 hasConceptScore W2907770449C147168706 @default.
- W2907770449 hasConceptScore W2907770449C154945302 @default.
- W2907770449 hasConceptScore W2907770449C185592680 @default.
- W2907770449 hasConceptScore W2907770449C33923547 @default.
- W2907770449 hasConceptScore W2907770449C41008148 @default.
- W2907770449 hasConceptScore W2907770449C50644808 @default.
- W2907770449 hasConceptScore W2907770449C55493867 @default.
- W2907770449 hasConceptScore W2907770449C63479239 @default.
- W2907770449 hasConceptScore W2907770449C80444323 @default.
- W2907770449 hasConceptScore W2907770449C81363708 @default.
- W2907770449 hasConceptScore W2907770449C8272713 @default.
- W2907770449 hasLocation W29077704491 @default.
- W2907770449 hasOpenAccess W2907770449 @default.
- W2907770449 hasPrimaryLocation W29077704491 @default.
- W2907770449 hasRelatedWork W2365327584 @default.
- W2907770449 hasRelatedWork W2396566817 @default.
- W2907770449 hasRelatedWork W2519456467 @default.
- W2907770449 hasRelatedWork W2747861677 @default.
- W2907770449 hasRelatedWork W2791891314 @default.
- W2907770449 hasRelatedWork W2886997576 @default.
- W2907770449 hasRelatedWork W2950004620 @default.
- W2907770449 hasRelatedWork W2954829150 @default.
- W2907770449 hasRelatedWork W2955286754 @default.
- W2907770449 hasRelatedWork W2962785940 @default.
- W2907770449 hasRelatedWork W2963421552 @default.
- W2907770449 hasRelatedWork W3035677100 @default.
- W2907770449 hasRelatedWork W3087755844 @default.
- W2907770449 hasRelatedWork W3160982157 @default.
- W2907770449 hasRelatedWork W3187395669 @default.
- W2907770449 hasRelatedWork W3188261512 @default.
- W2907770449 hasRelatedWork W3208827570 @default.
- W2907770449 hasRelatedWork W3211666987 @default.
- W2907770449 hasRelatedWork W592244745 @default.
- W2907770449 hasRelatedWork W2950507763 @default.
- W2907770449 isParatext "false" @default.
- W2907770449 isRetracted "false" @default.
- W2907770449 magId "2907770449" @default.
- W2907770449 workType "article" @default.