Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896475309> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W2896475309 abstract "End-to-end learning of communication systems enables joint optimization of transmitter and receiver, implemented as deep neural network-based autoencoders, over any type of channel and for an arbitrary performance metric. Recently, an alternating training procedure was proposed which eliminates the need for an explicit channel model. However, this approach requires feedback of real-valued losses from the receiver to the transmitter during training. In this paper, we first show that alternating training works even with a noisy feedback channel. Then, we design a system that learns to transmit real numbers over an unknown channel without a preexisting feedback link. Once trained, this feedback system can be used to communicate losses during alternating training of autoencoders. Evaluations over additive white Gaussian noise and Rayleigh block-fading channels show that end-to-end communication systems trained using the proposed feedback system achieve the same performance as when trained with a perfect feedback link." @default.
- W2896475309 created "2018-10-26" @default.
- W2896475309 creator A5062167670 @default.
- W2896475309 creator A5074728359 @default.
- W2896475309 creator A5076265502 @default.
- W2896475309 date "2019-06-03" @default.
- W2896475309 modified "2023-09-27" @default.
- W2896475309 title "Deep Reinforcement Learning Autoencoder with Noisy Feedback" @default.
- W2896475309 cites W1535810436 @default.
- W2896475309 cites W2155027007 @default.
- W2896475309 cites W2557283755 @default.
- W2896475309 cites W2734408173 @default.
- W2896475309 cites W2783002080 @default.
- W2896475309 cites W2796257214 @default.
- W2896475309 cites W2804208583 @default.
- W2896475309 cites W2889153869 @default.
- W2896475309 cites W2962964572 @default.
- W2896475309 cites W2964121744 @default.
- W2896475309 hasPublicationYear "2019" @default.
- W2896475309 type Work @default.
- W2896475309 sameAs 2896475309 @default.
- W2896475309 citedByCount "7" @default.
- W2896475309 countsByYear W28964753092019 @default.
- W2896475309 countsByYear W28964753092020 @default.
- W2896475309 countsByYear W28964753092021 @default.
- W2896475309 crossrefType "proceedings-article" @default.
- W2896475309 hasAuthorship W2896475309A5062167670 @default.
- W2896475309 hasAuthorship W2896475309A5074728359 @default.
- W2896475309 hasAuthorship W2896475309A5076265502 @default.
- W2896475309 hasBestOaLocation W28964753092 @default.
- W2896475309 hasConcept C101738243 @default.
- W2896475309 hasConcept C108583219 @default.
- W2896475309 hasConcept C154945302 @default.
- W2896475309 hasConcept C41008148 @default.
- W2896475309 hasConcept C97541855 @default.
- W2896475309 hasConceptScore W2896475309C101738243 @default.
- W2896475309 hasConceptScore W2896475309C108583219 @default.
- W2896475309 hasConceptScore W2896475309C154945302 @default.
- W2896475309 hasConceptScore W2896475309C41008148 @default.
- W2896475309 hasConceptScore W2896475309C97541855 @default.
- W2896475309 hasLocation W28964753091 @default.
- W2896475309 hasLocation W28964753092 @default.
- W2896475309 hasOpenAccess W2896475309 @default.
- W2896475309 hasPrimaryLocation W28964753091 @default.
- W2896475309 hasRelatedWork W2669956259 @default.
- W2896475309 hasRelatedWork W2766947113 @default.
- W2896475309 hasRelatedWork W2795314786 @default.
- W2896475309 hasRelatedWork W2939353110 @default.
- W2896475309 hasRelatedWork W2963510064 @default.
- W2896475309 hasRelatedWork W3165097609 @default.
- W2896475309 hasRelatedWork W3165463024 @default.
- W2896475309 hasRelatedWork W3209662401 @default.
- W2896475309 hasRelatedWork W4287178339 @default.
- W2896475309 hasRelatedWork W4292874285 @default.
- W2896475309 isParatext "false" @default.
- W2896475309 isRetracted "false" @default.
- W2896475309 magId "2896475309" @default.
- W2896475309 workType "article" @default.