Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385800794> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4385800794 abstract "Deep neural networks (DNNs) have been widely used for learning precoding policy to achieve good system performance with low computational complexity. However, existing DNNs for learning precoding cannot be generalized to the number of users. Consequently, the DNNs have to be retrained frequently, which incurs unaffordable computational cost for training, especially when the number of antennas is large. As a metric of time complexity, the number of floating-point operations (FLOPs) has been analyzed for inference in literature. Yet the time complexity of training DNNs for learning wireless policies has only been evaluated in terms of running time. To gain useful insight into developing deep learning methods with low-cost training, in this paper we derive the numbers of FLOPs of training three DNNs used for learning precoding, which are circular convolution neural network (CCNN), linear convolution neural network with fully-connected layers (F-LCNN), and fully-connected neural network (FNN). We then compare them with those of inference. Analytical results show that the ratio of the approximate numbers of FLOPs for training to those for inference depends on the numbers of epochs and training samples. Simulation results show that the time complexity of training scales with the number of antennas faster than that of inference, and the complexity of training the F-LCNN and FNN scales faster than that of training the CCNN." @default.
- W4385800794 created "2023-08-15" @default.
- W4385800794 creator A5063714268 @default.
- W4385800794 creator A5082950698 @default.
- W4385800794 date "2023-06-01" @default.
- W4385800794 modified "2023-10-16" @default.
- W4385800794 title "Number of FLOPs of Training DNNs for Learning Precoding" @default.
- W4385800794 cites W1932847118 @default.
- W4385800794 cites W2908498346 @default.
- W4385800794 cites W2963809228 @default.
- W4385800794 cites W3096252532 @default.
- W4385800794 cites W3099684761 @default.
- W4385800794 cites W3105095353 @default.
- W4385800794 cites W3111499798 @default.
- W4385800794 cites W3111885788 @default.
- W4385800794 cites W3134410998 @default.
- W4385800794 cites W3162334409 @default.
- W4385800794 cites W4280508843 @default.
- W4385800794 cites W4292794088 @default.
- W4385800794 cites W4298200086 @default.
- W4385800794 doi "https://doi.org/10.1109/vtc2023-spring57618.2023.10200945" @default.
- W4385800794 hasPublicationYear "2023" @default.
- W4385800794 type Work @default.
- W4385800794 citedByCount "0" @default.
- W4385800794 crossrefType "proceedings-article" @default.
- W4385800794 hasAuthorship W4385800794A5063714268 @default.
- W4385800794 hasAuthorship W4385800794A5082950698 @default.
- W4385800794 hasConcept C108583219 @default.
- W4385800794 hasConcept C11413529 @default.
- W4385800794 hasConcept C119857082 @default.
- W4385800794 hasConcept C127162648 @default.
- W4385800794 hasConcept C154945302 @default.
- W4385800794 hasConcept C160562895 @default.
- W4385800794 hasConcept C173608175 @default.
- W4385800794 hasConcept C179799912 @default.
- W4385800794 hasConcept C207987634 @default.
- W4385800794 hasConcept C2776214188 @default.
- W4385800794 hasConcept C3826847 @default.
- W4385800794 hasConcept C41008148 @default.
- W4385800794 hasConcept C45347329 @default.
- W4385800794 hasConcept C50644808 @default.
- W4385800794 hasConcept C76155785 @default.
- W4385800794 hasConceptScore W4385800794C108583219 @default.
- W4385800794 hasConceptScore W4385800794C11413529 @default.
- W4385800794 hasConceptScore W4385800794C119857082 @default.
- W4385800794 hasConceptScore W4385800794C127162648 @default.
- W4385800794 hasConceptScore W4385800794C154945302 @default.
- W4385800794 hasConceptScore W4385800794C160562895 @default.
- W4385800794 hasConceptScore W4385800794C173608175 @default.
- W4385800794 hasConceptScore W4385800794C179799912 @default.
- W4385800794 hasConceptScore W4385800794C207987634 @default.
- W4385800794 hasConceptScore W4385800794C2776214188 @default.
- W4385800794 hasConceptScore W4385800794C3826847 @default.
- W4385800794 hasConceptScore W4385800794C41008148 @default.
- W4385800794 hasConceptScore W4385800794C45347329 @default.
- W4385800794 hasConceptScore W4385800794C50644808 @default.
- W4385800794 hasConceptScore W4385800794C76155785 @default.
- W4385800794 hasLocation W43858007941 @default.
- W4385800794 hasOpenAccess W4385800794 @default.
- W4385800794 hasPrimaryLocation W43858007941 @default.
- W4385800794 hasRelatedWork W3014300295 @default.
- W4385800794 hasRelatedWork W3164822677 @default.
- W4385800794 hasRelatedWork W4223943233 @default.
- W4385800794 hasRelatedWork W4225161397 @default.
- W4385800794 hasRelatedWork W4250304930 @default.
- W4385800794 hasRelatedWork W4312200629 @default.
- W4385800794 hasRelatedWork W4360585206 @default.
- W4385800794 hasRelatedWork W4364306694 @default.
- W4385800794 hasRelatedWork W4380075502 @default.
- W4385800794 hasRelatedWork W4380086463 @default.
- W4385800794 isParatext "false" @default.
- W4385800794 isRetracted "false" @default.
- W4385800794 workType "article" @default.