Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281728148> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4281728148 endingPage "277" @default.
- W4281728148 startingPage "263" @default.
- W4281728148 abstract "The backpropagation (BP) neural network has been widely used in many fields. However, it is still a great challenge to design the architecture and obtain optimal parameters for BP neural networks. For improving the generalization performance, regularization is the most popular technique to train the BP neural networks. In this paper, we propose a novel BP algorithm with graph regularization (BPGR) to obtain optimal parameters, by imposing the graph regularization term to the error function. The essential idea is to force the latent features of hidden layer to be more concentrated, which enhances the generalization performance. Besides, the proposed modified graph regularization facilitates the calculation of gradient and is more capable to penalize the extreme values of weights. Furthermore, the graph regularization can also be integrated with deep neural networks to improve their generalization performance. In addition, we provide the convergence analysis of our method BPGR under some regularity conditions. By comparison on several datasets with five activation functions, experimental results validate the theoretical analysis and demonstrate outstanding performance of BPGR." @default.
- W4281728148 created "2022-06-13" @default.
- W4281728148 creator A5069143650 @default.
- W4281728148 creator A5090237325 @default.
- W4281728148 date "2022-08-01" @default.
- W4281728148 modified "2023-09-30" @default.
- W4281728148 title "A backpropagation learning algorithm with graph regularization for feedforward neural networks" @default.
- W4281728148 cites W1498436455 @default.
- W4281728148 cites W2011791191 @default.
- W4281728148 cites W2019797988 @default.
- W4281728148 cites W2056201402 @default.
- W4281728148 cites W2060346113 @default.
- W4281728148 cites W2083380015 @default.
- W4281728148 cites W2088350412 @default.
- W4281728148 cites W2106398669 @default.
- W4281728148 cites W2110179049 @default.
- W4281728148 cites W2111388763 @default.
- W4281728148 cites W2111719156 @default.
- W4281728148 cites W2115471292 @default.
- W4281728148 cites W2129664936 @default.
- W4281728148 cites W2130378394 @default.
- W4281728148 cites W2136279704 @default.
- W4281728148 cites W2153635508 @default.
- W4281728148 cites W2160815625 @default.
- W4281728148 cites W2165967751 @default.
- W4281728148 cites W2565516711 @default.
- W4281728148 cites W2592929672 @default.
- W4281728148 cites W2599383895 @default.
- W4281728148 cites W2730619644 @default.
- W4281728148 cites W2744958044 @default.
- W4281728148 cites W2758000438 @default.
- W4281728148 cites W2962834855 @default.
- W4281728148 cites W2990761096 @default.
- W4281728148 doi "https://doi.org/10.1016/j.ins.2022.05.121" @default.
- W4281728148 hasPublicationYear "2022" @default.
- W4281728148 type Work @default.
- W4281728148 citedByCount "5" @default.
- W4281728148 countsByYear W42817281482022 @default.
- W4281728148 countsByYear W42817281482023 @default.
- W4281728148 crossrefType "journal-article" @default.
- W4281728148 hasAuthorship W4281728148A5069143650 @default.
- W4281728148 hasAuthorship W4281728148A5090237325 @default.
- W4281728148 hasConcept C11413529 @default.
- W4281728148 hasConcept C132525143 @default.
- W4281728148 hasConcept C134306372 @default.
- W4281728148 hasConcept C135252773 @default.
- W4281728148 hasConcept C141718189 @default.
- W4281728148 hasConcept C152442038 @default.
- W4281728148 hasConcept C154945302 @default.
- W4281728148 hasConcept C155032097 @default.
- W4281728148 hasConcept C175202392 @default.
- W4281728148 hasConcept C177973122 @default.
- W4281728148 hasConcept C2776135515 @default.
- W4281728148 hasConcept C33923547 @default.
- W4281728148 hasConcept C38365724 @default.
- W4281728148 hasConcept C41008148 @default.
- W4281728148 hasConcept C47702885 @default.
- W4281728148 hasConcept C50644808 @default.
- W4281728148 hasConcept C80444323 @default.
- W4281728148 hasConcept C98359873 @default.
- W4281728148 hasConceptScore W4281728148C11413529 @default.
- W4281728148 hasConceptScore W4281728148C132525143 @default.
- W4281728148 hasConceptScore W4281728148C134306372 @default.
- W4281728148 hasConceptScore W4281728148C135252773 @default.
- W4281728148 hasConceptScore W4281728148C141718189 @default.
- W4281728148 hasConceptScore W4281728148C152442038 @default.
- W4281728148 hasConceptScore W4281728148C154945302 @default.
- W4281728148 hasConceptScore W4281728148C155032097 @default.
- W4281728148 hasConceptScore W4281728148C175202392 @default.
- W4281728148 hasConceptScore W4281728148C177973122 @default.
- W4281728148 hasConceptScore W4281728148C2776135515 @default.
- W4281728148 hasConceptScore W4281728148C33923547 @default.
- W4281728148 hasConceptScore W4281728148C38365724 @default.
- W4281728148 hasConceptScore W4281728148C41008148 @default.
- W4281728148 hasConceptScore W4281728148C47702885 @default.
- W4281728148 hasConceptScore W4281728148C50644808 @default.
- W4281728148 hasConceptScore W4281728148C80444323 @default.
- W4281728148 hasConceptScore W4281728148C98359873 @default.
- W4281728148 hasLocation W42817281481 @default.
- W4281728148 hasOpenAccess W4281728148 @default.
- W4281728148 hasPrimaryLocation W42817281481 @default.
- W4281728148 hasRelatedWork W1604847762 @default.
- W4281728148 hasRelatedWork W2119169819 @default.
- W4281728148 hasRelatedWork W2137699621 @default.
- W4281728148 hasRelatedWork W2160276773 @default.
- W4281728148 hasRelatedWork W2181577714 @default.
- W4281728148 hasRelatedWork W2391384657 @default.
- W4281728148 hasRelatedWork W246564837 @default.
- W4281728148 hasRelatedWork W2540179461 @default.
- W4281728148 hasRelatedWork W2550984594 @default.
- W4281728148 hasRelatedWork W4281728148 @default.
- W4281728148 hasVolume "607" @default.
- W4281728148 isParatext "false" @default.
- W4281728148 isRetracted "false" @default.
- W4281728148 workType "article" @default.