FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316661067> ?p ?o ?g. }

• W4316661067 endingPage "1461" @default.
• W4316661067 startingPage "1447" @default.
• W4316661067 abstract "Learning-based resource allocation can be implemented in real-time, but deep neural networks (DNNs) developed in other fields such as computer vision are with high training complexity and weak generalizability. Leveraging domain knowledge in communications is promising for learning wireless policies efficiently. In this paper, we propose a framework of integrating the Shannon formula with DNNs, and derive a data rate-based DNN (DRNN), for learning resource allocation by taking power allocation as an example. The DRNN is with an iterative structure with multiple update layers, each consisting of a pre-determined model function, an update network, and a dimension reduction network. To justify the iterative structure, we prove the existence of an iteration function that converges to the optimal policy for the update layer to learn. To justify the structure of each update layer, we provide the conditions for the iteration function to be a composite function of the model function. We further incorporate permutation equivariance properties into the DRNN. Simulation results show that the numbers of training samples and free parameters, and the training time to achieve a desired system performance can be reduced remarkably by harnessing the data rate model and PE prior." @default.
• W4316661067 created "2023-01-17" @default.
• W4316661067 creator A5000108260 @default.
• W4316661067 creator A5038465404 @default.
• W4316661067 date "2023-03-01" @default.
• W4316661067 modified "2023-10-16" @default.
• W4316661067 title "Deep Neural Networks With Data Rate Model: Learning Power Allocation Efficiently" @default.
• W4316661067 cites W1994887634 @default.
• W4316661067 cites W2031132992 @default.
• W4316661067 cites W2037707796 @default.
• W4316661067 cites W2044892816 @default.
• W4316661067 cites W2060821751 @default.
• W4316661067 cites W2100755644 @default.
• W4316661067 cites W2106434019 @default.
• W4316661067 cites W2112820013 @default.
• W4316661067 cites W2286275639 @default.
• W4316661067 cites W2788350651 @default.
• W4316661067 cites W2797462110 @default.
• W4316661067 cites W2804075771 @default.
• W4316661067 cites W2908498346 @default.
• W4316661067 cites W2918342144 @default.
• W4316661067 cites W2919115771 @default.
• W4316661067 cites W2963101290 @default.
• W4316661067 cites W2963504849 @default.
• W4316661067 cites W2963809228 @default.
• W4316661067 cites W2964021722 @default.
• W4316661067 cites W2969580338 @default.
• W4316661067 cites W2971598376 @default.
• W4316661067 cites W2979880859 @default.
• W4316661067 cites W2981598692 @default.
• W4316661067 cites W2991155877 @default.
• W4316661067 cites W2992716901 @default.
• W4316661067 cites W3008026851 @default.
• W4316661067 cites W3012083412 @default.
• W4316661067 cites W3016146955 @default.
• W4316661067 cites W3032666109 @default.
• W4316661067 cites W3095613678 @default.
• W4316661067 cites W3096252532 @default.
• W4316661067 cites W3111499798 @default.
• W4316661067 cites W3111885788 @default.
• W4316661067 cites W3152787073 @default.
• W4316661067 cites W3158226575 @default.
• W4316661067 cites W3189854358 @default.
• W4316661067 cites W3203664723 @default.
• W4316661067 cites W3212630591 @default.
• W4316661067 cites W4280508843 @default.
• W4316661067 cites W4378974380 @default.
• W4316661067 doi "https://doi.org/10.1109/tcomm.2023.3237241" @default.
• W4316661067 hasPublicationYear "2023" @default.
• W4316661067 type Work @default.
• W4316661067 citedByCount "0" @default.
• W4316661067 crossrefType "journal-article" @default.
• W4316661067 hasAuthorship W4316661067A5000108260 @default.
• W4316661067 hasAuthorship W4316661067A5038465404 @default.
• W4316661067 hasConcept C105795698 @default.
• W4316661067 hasConcept C108583219 @default.
• W4316661067 hasConcept C11413529 @default.
• W4316661067 hasConcept C119857082 @default.
• W4316661067 hasConcept C126255220 @default.
• W4316661067 hasConcept C127162648 @default.
• W4316661067 hasConcept C14036430 @default.
• W4316661067 hasConcept C154945302 @default.
• W4316661067 hasConcept C159694833 @default.
• W4316661067 hasConcept C27158222 @default.
• W4316661067 hasConcept C29202148 @default.
• W4316661067 hasConcept C31258907 @default.
• W4316661067 hasConcept C33923547 @default.
• W4316661067 hasConcept C41008148 @default.
• W4316661067 hasConcept C50644808 @default.
• W4316661067 hasConcept C57869625 @default.
• W4316661067 hasConcept C78458016 @default.
• W4316661067 hasConcept C86803240 @default.
• W4316661067 hasConceptScore W4316661067C105795698 @default.
• W4316661067 hasConceptScore W4316661067C108583219 @default.
• W4316661067 hasConceptScore W4316661067C11413529 @default.
• W4316661067 hasConceptScore W4316661067C119857082 @default.
• W4316661067 hasConceptScore W4316661067C126255220 @default.
• W4316661067 hasConceptScore W4316661067C127162648 @default.
• W4316661067 hasConceptScore W4316661067C14036430 @default.
• W4316661067 hasConceptScore W4316661067C154945302 @default.
• W4316661067 hasConceptScore W4316661067C159694833 @default.
• W4316661067 hasConceptScore W4316661067C27158222 @default.
• W4316661067 hasConceptScore W4316661067C29202148 @default.
• W4316661067 hasConceptScore W4316661067C31258907 @default.
• W4316661067 hasConceptScore W4316661067C33923547 @default.
• W4316661067 hasConceptScore W4316661067C41008148 @default.
• W4316661067 hasConceptScore W4316661067C50644808 @default.
• W4316661067 hasConceptScore W4316661067C57869625 @default.
• W4316661067 hasConceptScore W4316661067C78458016 @default.
• W4316661067 hasConceptScore W4316661067C86803240 @default.
• W4316661067 hasFunder F4320321001 @default.
• W4316661067 hasIssue "3" @default.
• W4316661067 hasLocation W43166610671 @default.
• W4316661067 hasOpenAccess W4316661067 @default.
• W4316661067 hasPrimaryLocation W43166610671 @default.
• W4316661067 hasRelatedWork W3014300295 @default.
• W4316661067 hasRelatedWork W3164822677 @default.
• W4316661067 hasRelatedWork W4223943233 @default.

• next