Matches in SemOpenAlex for { <https://semopenalex.org/work/W2936697624> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2936697624 endingPage "1192" @default.
- W2936697624 startingPage "1182" @default.
- W2936697624 abstract "For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length regime, as it requires non-trivial tuning of hand-crafted codes and assumes infinite computational power for decoding. In this work, we propose to jointly learn the encoding and decoding processes using a new discrete variational autoencoder model. By adding noise into the latent codes to simulate the channel during training, we learn to both compress and error-correct given a fixed bit-length and computational budget. We obtain codes that are not only competitive against several separation schemes, but also learn useful robust representations of the data for downstream tasks such as classification. Finally, inference amortization yields an extremely fast neural decoder, almost an order of magnitude faster compared to standard decoding methods based on iterative belief propagation." @default.
- W2936697624 created "2019-04-25" @default.
- W2936697624 creator A5014409944 @default.
- W2936697624 creator A5043344688 @default.
- W2936697624 creator A5045177980 @default.
- W2936697624 creator A5050928433 @default.
- W2936697624 creator A5091179481 @default.
- W2936697624 date "2019-05-24" @default.
- W2936697624 modified "2023-09-23" @default.
- W2936697624 title "Neural Joint Source-Channel Coding" @default.
- W2936697624 hasPublicationYear "2019" @default.
- W2936697624 type Work @default.
- W2936697624 sameAs 2936697624 @default.
- W2936697624 citedByCount "15" @default.
- W2936697624 countsByYear W29366976242018 @default.
- W2936697624 countsByYear W29366976242019 @default.
- W2936697624 countsByYear W29366976242020 @default.
- W2936697624 countsByYear W29366976242021 @default.
- W2936697624 crossrefType "proceedings-article" @default.
- W2936697624 hasAuthorship W2936697624A5014409944 @default.
- W2936697624 hasAuthorship W2936697624A5043344688 @default.
- W2936697624 hasAuthorship W2936697624A5045177980 @default.
- W2936697624 hasAuthorship W2936697624A5050928433 @default.
- W2936697624 hasAuthorship W2936697624A5091179481 @default.
- W2936697624 hasConcept C101738243 @default.
- W2936697624 hasConcept C105795698 @default.
- W2936697624 hasConcept C111919701 @default.
- W2936697624 hasConcept C11413529 @default.
- W2936697624 hasConcept C118505674 @default.
- W2936697624 hasConcept C125411270 @default.
- W2936697624 hasConcept C127162648 @default.
- W2936697624 hasConcept C152948882 @default.
- W2936697624 hasConcept C154945302 @default.
- W2936697624 hasConcept C157125643 @default.
- W2936697624 hasConcept C179518139 @default.
- W2936697624 hasConcept C193969084 @default.
- W2936697624 hasConcept C33923547 @default.
- W2936697624 hasConcept C41008148 @default.
- W2936697624 hasConcept C50644808 @default.
- W2936697624 hasConcept C57273362 @default.
- W2936697624 hasConcept C76155785 @default.
- W2936697624 hasConcept C80444323 @default.
- W2936697624 hasConceptScore W2936697624C101738243 @default.
- W2936697624 hasConceptScore W2936697624C105795698 @default.
- W2936697624 hasConceptScore W2936697624C111919701 @default.
- W2936697624 hasConceptScore W2936697624C11413529 @default.
- W2936697624 hasConceptScore W2936697624C118505674 @default.
- W2936697624 hasConceptScore W2936697624C125411270 @default.
- W2936697624 hasConceptScore W2936697624C127162648 @default.
- W2936697624 hasConceptScore W2936697624C152948882 @default.
- W2936697624 hasConceptScore W2936697624C154945302 @default.
- W2936697624 hasConceptScore W2936697624C157125643 @default.
- W2936697624 hasConceptScore W2936697624C179518139 @default.
- W2936697624 hasConceptScore W2936697624C193969084 @default.
- W2936697624 hasConceptScore W2936697624C33923547 @default.
- W2936697624 hasConceptScore W2936697624C41008148 @default.
- W2936697624 hasConceptScore W2936697624C50644808 @default.
- W2936697624 hasConceptScore W2936697624C57273362 @default.
- W2936697624 hasConceptScore W2936697624C76155785 @default.
- W2936697624 hasConceptScore W2936697624C80444323 @default.
- W2936697624 hasLocation W29366976241 @default.
- W2936697624 hasOpenAccess W2936697624 @default.
- W2936697624 hasPrimaryLocation W29366976241 @default.
- W2936697624 hasRelatedWork W1995875735 @default.
- W2936697624 hasRelatedWork W2099111195 @default.
- W2936697624 hasRelatedWork W2163605009 @default.
- W2936697624 hasRelatedWork W2186701903 @default.
- W2936697624 hasRelatedWork W2194775991 @default.
- W2936697624 hasRelatedWork W2605258629 @default.
- W2936697624 hasRelatedWork W2666368276 @default.
- W2936697624 hasRelatedWork W2734408173 @default.
- W2936697624 hasRelatedWork W2946889564 @default.
- W2936697624 hasRelatedWork W2951542323 @default.
- W2936697624 hasRelatedWork W2952897440 @default.
- W2936697624 hasRelatedWork W2963174256 @default.
- W2936697624 hasRelatedWork W2963770864 @default.
- W2936697624 hasRelatedWork W2963799213 @default.
- W2936697624 hasRelatedWork W2971153810 @default.
- W2936697624 hasRelatedWork W3014802836 @default.
- W2936697624 hasRelatedWork W3043914740 @default.
- W2936697624 hasRelatedWork W3049038845 @default.
- W2936697624 hasRelatedWork W3118608800 @default.
- W2936697624 hasRelatedWork W330061002 @default.
- W2936697624 isParatext "false" @default.
- W2936697624 isRetracted "false" @default.
- W2936697624 magId "2936697624" @default.
- W2936697624 workType "article" @default.