Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378903438> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4378903438 abstract "Abstract There are several methods that have been discovered to improve the performance of Deep Learning (DL). Many of these methods reached the best performance of their models by tuning several parameters such as Transfer Learning, Data augmentation, Dropout, and Batch Normalization, while other selects the best optimizer and the best architecture for their model. This paper is mainly concerned with the optimization algorithms in DL. It proposes a modified version of Root Mean Squared Propagation (RMSProp) algorithm, called NRMSProp, to improve the speed of convergence, and to find the minimum of the loss function quicker than the original RMSProp optimizer. Moreover, NRMSProp takes the original algorithm, RMSProp, a step further by using the advantages of Nesterov Accelerated Gradient (NAG). It also takes in consideration the direction of the gradient at the next step, with respect to the history of the previous gradients, and adapts the value of the learning rate. As a result, this modification helps NRMSProp to convergence quicker than the original RMSProp, without any increase in the complexity of the RMSProp. In this work, many experiments had been conducted to evaluate the performance of NRMSProp with performing several tests with deep Convolution Neural Networks (CNNs) using different datasets on RMSProp, Adam, and NRMSProp optimizers. The experimental results showed that NRMSProp has achieved effective performance, and accuracy up to 0.97 in most cases, in comparison to RMSProp and Adam optimizers, without any increase in the complexity of the algorithm and with fine amount of memory and time." @default.
- W4378903438 created "2023-06-01" @default.
- W4378903438 creator A5039501216 @default.
- W4378903438 creator A5080087070 @default.
- W4378903438 creator A5085089542 @default.
- W4378903438 creator A5092059515 @default.
- W4378903438 date "2023-05-31" @default.
- W4378903438 modified "2023-09-25" @default.
- W4378903438 title "Improving the efficiency of RMSProp optimizer by utilizing Nestrove in deep learning" @default.
- W4378903438 cites W2002517365 @default.
- W4378903438 cites W2062227835 @default.
- W4378903438 cites W2108598243 @default.
- W4378903438 cites W2167634486 @default.
- W4378903438 cites W2194775991 @default.
- W4378903438 cites W2519796145 @default.
- W4378903438 cites W2782970864 @default.
- W4378903438 cites W2883837659 @default.
- W4378903438 cites W2942231644 @default.
- W4378903438 cites W2945367617 @default.
- W4378903438 cites W2969534524 @default.
- W4378903438 cites W2990426214 @default.
- W4378903438 cites W3004577623 @default.
- W4378903438 cites W4242121546 @default.
- W4378903438 cites W4282966553 @default.
- W4378903438 cites W4295789340 @default.
- W4378903438 doi "https://doi.org/10.1038/s41598-023-35663-x" @default.
- W4378903438 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37258633" @default.
- W4378903438 hasPublicationYear "2023" @default.
- W4378903438 type Work @default.
- W4378903438 citedByCount "0" @default.
- W4378903438 crossrefType "journal-article" @default.
- W4378903438 hasAuthorship W4378903438A5039501216 @default.
- W4378903438 hasAuthorship W4378903438A5080087070 @default.
- W4378903438 hasAuthorship W4378903438A5085089542 @default.
- W4378903438 hasAuthorship W4378903438A5092059515 @default.
- W4378903438 hasBestOaLocation W43789034381 @default.
- W4378903438 hasConcept C108583219 @default.
- W4378903438 hasConcept C11413529 @default.
- W4378903438 hasConcept C136886441 @default.
- W4378903438 hasConcept C144024400 @default.
- W4378903438 hasConcept C154945302 @default.
- W4378903438 hasConcept C162324750 @default.
- W4378903438 hasConcept C19165224 @default.
- W4378903438 hasConcept C2777303404 @default.
- W4378903438 hasConcept C41008148 @default.
- W4378903438 hasConcept C50522688 @default.
- W4378903438 hasConcept C81184566 @default.
- W4378903438 hasConceptScore W4378903438C108583219 @default.
- W4378903438 hasConceptScore W4378903438C11413529 @default.
- W4378903438 hasConceptScore W4378903438C136886441 @default.
- W4378903438 hasConceptScore W4378903438C144024400 @default.
- W4378903438 hasConceptScore W4378903438C154945302 @default.
- W4378903438 hasConceptScore W4378903438C162324750 @default.
- W4378903438 hasConceptScore W4378903438C19165224 @default.
- W4378903438 hasConceptScore W4378903438C2777303404 @default.
- W4378903438 hasConceptScore W4378903438C41008148 @default.
- W4378903438 hasConceptScore W4378903438C50522688 @default.
- W4378903438 hasConceptScore W4378903438C81184566 @default.
- W4378903438 hasFunder F4320325716 @default.
- W4378903438 hasIssue "1" @default.
- W4378903438 hasLocation W43789034381 @default.
- W4378903438 hasLocation W43789034382 @default.
- W4378903438 hasOpenAccess W4378903438 @default.
- W4378903438 hasPrimaryLocation W43789034381 @default.
- W4378903438 hasRelatedWork W1975200206 @default.
- W4378903438 hasRelatedWork W2128886773 @default.
- W4378903438 hasRelatedWork W2280258626 @default.
- W4378903438 hasRelatedWork W2388528661 @default.
- W4378903438 hasRelatedWork W2410085756 @default.
- W4378903438 hasRelatedWork W2794115703 @default.
- W4378903438 hasRelatedWork W2963958000 @default.
- W4378903438 hasRelatedWork W2992103062 @default.
- W4378903438 hasRelatedWork W3156188347 @default.
- W4378903438 hasRelatedWork W4301772310 @default.
- W4378903438 hasVolume "13" @default.
- W4378903438 isParatext "false" @default.
- W4378903438 isRetracted "false" @default.
- W4378903438 workType "article" @default.