Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949207763> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2949207763 abstract "Artificial neural networks have gone through a recent rise in popularity, achieving state-of-the-art results in various fields, including image classification, speech recognition, and automated control. Both the performance and computational complexity of such models are heavily dependant on the design of characteristic hyper-parameters (e.g., number of hidden layers, nodes per layer, or choice of activation functions), which have traditionally been optimized manually. With machine learning penetrating low-power mobile and embedded areas, the need to optimize not only for performance (accuracy), but also for implementation complexity, becomes paramount. In this work, we present a multi-objective design space exploration method that reduces the number of solution networks trained and evaluated through response surface modelling. Given spaces which can easily exceed 1020 solutions, manually designing a near-optimal architecture is unlikely as opportunities to reduce network complexity, while maintaining performance, may be overlooked. This problem is exacerbated by the fact that hyper-parameters which perform well on specific datasets may yield sub-par results on others, and must therefore be designed on a per-application basis. In our work, machine learning is leveraged by training an artificial neural network to predict the performance of future candidate networks. The method is evaluated on the MNIST and CIFAR-10 image datasets, optimizing for both recognition accuracy and computational complexity. Experimental results demonstrate that the proposed method can closely approximate the Pareto-optimal front, while only exploring a small fraction of the design space." @default.
- W2949207763 created "2019-06-27" @default.
- W2949207763 creator A5031182338 @default.
- W2949207763 creator A5034701871 @default.
- W2949207763 creator A5073429636 @default.
- W2949207763 creator A5091600002 @default.
- W2949207763 date "2016-11-07" @default.
- W2949207763 modified "2023-09-27" @default.
- W2949207763 title "Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization" @default.
- W2949207763 cites W1522301498 @default.
- W2949207763 cites W1606347560 @default.
- W2949207763 cites W1617462244 @default.
- W2949207763 cites W1902934009 @default.
- W2949207763 cites W1978381081 @default.
- W2949207763 cites W2056760934 @default.
- W2949207763 cites W2097998348 @default.
- W2949207763 cites W2106411961 @default.
- W2949207763 cites W2112796928 @default.
- W2949207763 cites W2133796295 @default.
- W2949207763 cites W2143612262 @default.
- W2949207763 cites W2156679542 @default.
- W2949207763 cites W2250904038 @default.
- W2949207763 cites W2266822037 @default.
- W2949207763 cites W2546302380 @default.
- W2949207763 cites W2553858835 @default.
- W2949207763 cites W2919115771 @default.
- W2949207763 cites W2949117887 @default.
- W2949207763 cites W2963674932 @default.
- W2949207763 cites W3118608800 @default.
- W2949207763 hasPublicationYear "2016" @default.
- W2949207763 type Work @default.
- W2949207763 sameAs 2949207763 @default.
- W2949207763 citedByCount "6" @default.
- W2949207763 countsByYear W29492077632017 @default.
- W2949207763 countsByYear W29492077632018 @default.
- W2949207763 countsByYear W29492077632019 @default.
- W2949207763 crossrefType "posted-content" @default.
- W2949207763 hasAuthorship W2949207763A5031182338 @default.
- W2949207763 hasAuthorship W2949207763A5034701871 @default.
- W2949207763 hasAuthorship W2949207763A5073429636 @default.
- W2949207763 hasAuthorship W2949207763A5091600002 @default.
- W2949207763 hasConcept C11413529 @default.
- W2949207763 hasConcept C115961682 @default.
- W2949207763 hasConcept C119857082 @default.
- W2949207763 hasConcept C149635348 @default.
- W2949207763 hasConcept C154945302 @default.
- W2949207763 hasConcept C179799912 @default.
- W2949207763 hasConcept C190502265 @default.
- W2949207763 hasConcept C2776221188 @default.
- W2949207763 hasConcept C41008148 @default.
- W2949207763 hasConcept C50644808 @default.
- W2949207763 hasConcept C75294576 @default.
- W2949207763 hasConceptScore W2949207763C11413529 @default.
- W2949207763 hasConceptScore W2949207763C115961682 @default.
- W2949207763 hasConceptScore W2949207763C119857082 @default.
- W2949207763 hasConceptScore W2949207763C149635348 @default.
- W2949207763 hasConceptScore W2949207763C154945302 @default.
- W2949207763 hasConceptScore W2949207763C179799912 @default.
- W2949207763 hasConceptScore W2949207763C190502265 @default.
- W2949207763 hasConceptScore W2949207763C2776221188 @default.
- W2949207763 hasConceptScore W2949207763C41008148 @default.
- W2949207763 hasConceptScore W2949207763C50644808 @default.
- W2949207763 hasConceptScore W2949207763C75294576 @default.
- W2949207763 hasLocation W29492077631 @default.
- W2949207763 hasOpenAccess W2949207763 @default.
- W2949207763 hasPrimaryLocation W29492077631 @default.
- W2949207763 hasRelatedWork W2108598243 @default.
- W2949207763 hasRelatedWork W2181028625 @default.
- W2949207763 hasRelatedWork W2507936800 @default.
- W2949207763 hasRelatedWork W2534788641 @default.
- W2949207763 hasRelatedWork W2739997491 @default.
- W2949207763 hasRelatedWork W2807631648 @default.
- W2949207763 hasRelatedWork W2904473220 @default.
- W2949207763 hasRelatedWork W2913099907 @default.
- W2949207763 hasRelatedWork W2920230375 @default.
- W2949207763 hasRelatedWork W2943539461 @default.
- W2949207763 hasRelatedWork W2948525304 @default.
- W2949207763 hasRelatedWork W2964062240 @default.
- W2949207763 hasRelatedWork W2965214894 @default.
- W2949207763 hasRelatedWork W3001965986 @default.
- W2949207763 hasRelatedWork W3016768016 @default.
- W2949207763 hasRelatedWork W3023750926 @default.
- W2949207763 hasRelatedWork W3085858322 @default.
- W2949207763 hasRelatedWork W3096140875 @default.
- W2949207763 hasRelatedWork W3130774444 @default.
- W2949207763 hasRelatedWork W3206105267 @default.
- W2949207763 isParatext "false" @default.
- W2949207763 isRetracted "false" @default.
- W2949207763 magId "2949207763" @default.
- W2949207763 workType "article" @default.