Matches in SemOpenAlex for { <https://semopenalex.org/work/W2884166952> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2884166952 endingPage "367" @default.
- W2884166952 startingPage "359" @default.
- W2884166952 abstract "Abstract Hyperparameters determine layer architecture in the feature extraction step of a convolutional neural network (CNN), and this affects classification accuracy and learning time. In this paper, we propose a method to improve CNN performance by hyperparameter tuning in the feature extraction step of CNN. In the proposed method, the hyperparameter is adjusted using a parameter-setting-free harmony search (PSF-HS) algorithm, which is a metaheuristic optimization method. In the PSF-HS algorithm, the hyperparameter to be adjusted is set as the harmony, and harmony memory is generated after generating the harmony. Harmony memory is updated based on the loss of a CNN. A simulation using CNN architecture with reference to LeNet-5 and a MNIST dataset, and a simulation using the CNN architecture with reference to CifarNet and a Cifar-10 dataset are performed. By two simulations, it is possible to improve the performance by tuning the hyperparameters in CNN architectures proposed in the past." @default.
- W2884166952 created "2018-08-03" @default.
- W2884166952 creator A5022121912 @default.
- W2884166952 creator A5063157469 @default.
- W2884166952 creator A5064069488 @default.
- W2884166952 date "2018-11-01" @default.
- W2884166952 modified "2023-10-16" @default.
- W2884166952 title "Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm" @default.
- W2884166952 cites W1964525006 @default.
- W2884166952 cites W1985334587 @default.
- W2884166952 cites W2001771035 @default.
- W2884166952 cites W2073147782 @default.
- W2884166952 cites W2112796928 @default.
- W2884166952 cites W2120284346 @default.
- W2884166952 cites W2144354855 @default.
- W2884166952 cites W2502417921 @default.
- W2884166952 cites W2607176717 @default.
- W2884166952 cites W2735450835 @default.
- W2884166952 cites W2919115771 @default.
- W2884166952 doi "https://doi.org/10.1016/j.ijleo.2018.07.044" @default.
- W2884166952 hasPublicationYear "2018" @default.
- W2884166952 type Work @default.
- W2884166952 sameAs 2884166952 @default.
- W2884166952 citedByCount "68" @default.
- W2884166952 countsByYear W28841669522019 @default.
- W2884166952 countsByYear W28841669522020 @default.
- W2884166952 countsByYear W28841669522021 @default.
- W2884166952 countsByYear W28841669522022 @default.
- W2884166952 countsByYear W28841669522023 @default.
- W2884166952 crossrefType "journal-article" @default.
- W2884166952 hasAuthorship W2884166952A5022121912 @default.
- W2884166952 hasAuthorship W2884166952A5063157469 @default.
- W2884166952 hasAuthorship W2884166952A5064069488 @default.
- W2884166952 hasConcept C10485038 @default.
- W2884166952 hasConcept C11413529 @default.
- W2884166952 hasConcept C119857082 @default.
- W2884166952 hasConcept C12267149 @default.
- W2884166952 hasConcept C125583679 @default.
- W2884166952 hasConcept C126255220 @default.
- W2884166952 hasConcept C154945302 @default.
- W2884166952 hasConcept C33099171 @default.
- W2884166952 hasConcept C33923547 @default.
- W2884166952 hasConcept C41008148 @default.
- W2884166952 hasConcept C81363708 @default.
- W2884166952 hasConcept C8642999 @default.
- W2884166952 hasConceptScore W2884166952C10485038 @default.
- W2884166952 hasConceptScore W2884166952C11413529 @default.
- W2884166952 hasConceptScore W2884166952C119857082 @default.
- W2884166952 hasConceptScore W2884166952C12267149 @default.
- W2884166952 hasConceptScore W2884166952C125583679 @default.
- W2884166952 hasConceptScore W2884166952C126255220 @default.
- W2884166952 hasConceptScore W2884166952C154945302 @default.
- W2884166952 hasConceptScore W2884166952C33099171 @default.
- W2884166952 hasConceptScore W2884166952C33923547 @default.
- W2884166952 hasConceptScore W2884166952C41008148 @default.
- W2884166952 hasConceptScore W2884166952C81363708 @default.
- W2884166952 hasConceptScore W2884166952C8642999 @default.
- W2884166952 hasLocation W28841669521 @default.
- W2884166952 hasOpenAccess W2884166952 @default.
- W2884166952 hasPrimaryLocation W28841669521 @default.
- W2884166952 hasRelatedWork W2884166952 @default.
- W2884166952 hasRelatedWork W3014750173 @default.
- W2884166952 hasRelatedWork W3033561277 @default.
- W2884166952 hasRelatedWork W3152685838 @default.
- W2884166952 hasRelatedWork W3199608561 @default.
- W2884166952 hasRelatedWork W4280535922 @default.
- W2884166952 hasRelatedWork W4281646320 @default.
- W2884166952 hasRelatedWork W4283697347 @default.
- W2884166952 hasRelatedWork W4295309597 @default.
- W2884166952 hasRelatedWork W4298144215 @default.
- W2884166952 hasVolume "172" @default.
- W2884166952 isParatext "false" @default.
- W2884166952 isRetracted "false" @default.
- W2884166952 magId "2884166952" @default.
- W2884166952 workType "article" @default.