Matches in SemOpenAlex for { <https://semopenalex.org/work/W3121013024> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3121013024 endingPage "e338" @default.
- W3121013024 startingPage "e338" @default.
- W3121013024 abstract "In this study, we model a CNN hyper-parameter optimization problem as a bi-criteria optimization problem, where the first objective being the classification accuracy and the second objective being the computational complexity which is measured in terms of the number of floating point operations. For this bi-criteria optimization problem, we develop a Multi-Objective Simulated Annealing (MOSA) algorithm for obtaining high-quality solutions in terms of both objectives. CIFAR-10 is selected as the benchmark dataset, and the MOSA trade-off fronts obtained for this dataset are compared to the fronts generated by a single-objective Simulated Annealing (SA) algorithm with respect to several front evaluation metrics such as generational distance, spacing and spread. The comparison results suggest that the MOSA algorithm is able to search the objective space more effectively than the SA method. For each of these methods, some front solutions are selected for longer training in order to see their actual performance on the original test set. Again, the results state that the MOSA performs better than the SA under multi-objective setting. The performance of the MOSA configurations are also compared to other search generated and human designed state-of-the-art architectures. It is shown that the network configurations generated by the MOSA are not dominated by those architectures, and the proposed method can be of great use when the computational complexity is as important as the test accuracy." @default.
- W3121013024 created "2021-01-18" @default.
- W3121013024 creator A5053676475 @default.
- W3121013024 creator A5074857800 @default.
- W3121013024 date "2021-01-04" @default.
- W3121013024 modified "2023-10-01" @default.
- W3121013024 title "Multi-objective simulated annealing for hyper-parameter optimization in convolutional neural networks" @default.
- W3121013024 cites W1559956479 @default.
- W3121013024 cites W1947484358 @default.
- W3121013024 cites W1968535060 @default.
- W3121013024 cites W1984078293 @default.
- W3121013024 cites W1986697600 @default.
- W3121013024 cites W2003412293 @default.
- W3121013024 cites W2024060531 @default.
- W3121013024 cites W2048424596 @default.
- W3121013024 cites W2085830763 @default.
- W3121013024 cites W2098907614 @default.
- W3121013024 cites W2104492856 @default.
- W3121013024 cites W2112796928 @default.
- W3121013024 cites W2114725328 @default.
- W3121013024 cites W2117539524 @default.
- W3121013024 cites W2125502051 @default.
- W3121013024 cites W2125899728 @default.
- W3121013024 cites W2152195021 @default.
- W3121013024 cites W2953308748 @default.
- W3121013024 cites W2965658867 @default.
- W3121013024 cites W2981009032 @default.
- W3121013024 cites W3011131643 @default.
- W3121013024 cites W4211116959 @default.
- W3121013024 cites W4250503569 @default.
- W3121013024 doi "https://doi.org/10.7717/peerj-cs.338" @default.
- W3121013024 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7924536" @default.
- W3121013024 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33816989" @default.
- W3121013024 hasPublicationYear "2021" @default.
- W3121013024 type Work @default.
- W3121013024 sameAs 3121013024 @default.
- W3121013024 citedByCount "8" @default.
- W3121013024 countsByYear W31210130242021 @default.
- W3121013024 countsByYear W31210130242022 @default.
- W3121013024 countsByYear W31210130242023 @default.
- W3121013024 crossrefType "journal-article" @default.
- W3121013024 hasAuthorship W3121013024A5053676475 @default.
- W3121013024 hasAuthorship W3121013024A5074857800 @default.
- W3121013024 hasBestOaLocation W31210130241 @default.
- W3121013024 hasConcept C11413529 @default.
- W3121013024 hasConcept C126255220 @default.
- W3121013024 hasConcept C126980161 @default.
- W3121013024 hasConcept C13280743 @default.
- W3121013024 hasConcept C154945302 @default.
- W3121013024 hasConcept C185798385 @default.
- W3121013024 hasConcept C205649164 @default.
- W3121013024 hasConcept C33923547 @default.
- W3121013024 hasConcept C41008148 @default.
- W3121013024 hasConcept C50644808 @default.
- W3121013024 hasConcept C81363708 @default.
- W3121013024 hasConceptScore W3121013024C11413529 @default.
- W3121013024 hasConceptScore W3121013024C126255220 @default.
- W3121013024 hasConceptScore W3121013024C126980161 @default.
- W3121013024 hasConceptScore W3121013024C13280743 @default.
- W3121013024 hasConceptScore W3121013024C154945302 @default.
- W3121013024 hasConceptScore W3121013024C185798385 @default.
- W3121013024 hasConceptScore W3121013024C205649164 @default.
- W3121013024 hasConceptScore W3121013024C33923547 @default.
- W3121013024 hasConceptScore W3121013024C41008148 @default.
- W3121013024 hasConceptScore W3121013024C50644808 @default.
- W3121013024 hasConceptScore W3121013024C81363708 @default.
- W3121013024 hasLocation W31210130241 @default.
- W3121013024 hasLocation W31210130242 @default.
- W3121013024 hasOpenAccess W3121013024 @default.
- W3121013024 hasPrimaryLocation W31210130241 @default.
- W3121013024 hasRelatedWork W112744582 @default.
- W3121013024 hasRelatedWork W1485630101 @default.
- W3121013024 hasRelatedWork W155607310 @default.
- W3121013024 hasRelatedWork W2392110728 @default.
- W3121013024 hasRelatedWork W2498017833 @default.
- W3121013024 hasRelatedWork W2748454020 @default.
- W3121013024 hasRelatedWork W2791491984 @default.
- W3121013024 hasRelatedWork W3013330614 @default.
- W3121013024 hasRelatedWork W3016958897 @default.
- W3121013024 hasRelatedWork W3181746755 @default.
- W3121013024 hasVolume "7" @default.
- W3121013024 isParatext "false" @default.
- W3121013024 isRetracted "false" @default.
- W3121013024 magId "3121013024" @default.
- W3121013024 workType "article" @default.