FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088798822> ?p ?o ?g. }

• W3088798822 endingPage "291" @default.
• W3088798822 startingPage "277" @default.
• W3088798822 abstract "Convolutional neural networks (CNNs) are the backbones of deep learning paradigms for numerous vision tasks. Early advancements in CNN architectures are primarily driven by human expertise and by elaborate design processes. Recently, neural architecture search was proposed with the aim of automating the network design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: 1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario and 2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient design of architectures that are competitive and in most cases outperform both manually and automatically designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature." @default.
• W3088798822 created "2020-10-01" @default.
• W3088798822 creator A5004837138 @default.
• W3088798822 creator A5027687139 @default.
• W3088798822 creator A5031717929 @default.
• W3088798822 creator A5033455019 @default.
• W3088798822 creator A5034853476 @default.
• W3088798822 creator A5068379698 @default.
• W3088798822 creator A5088394271 @default.
• W3088798822 date "2021-04-01" @default.
• W3088798822 modified "2023-09-29" @default.
• W3088798822 title "Multiobjective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification" @default.
• W3088798822 cites W1995861141 @default.
• W3088798822 cites W2000295051 @default.
• W3088798822 cites W2071707442 @default.
• W3088798822 cites W2097117768 @default.
• W3088798822 cites W2102006495 @default.
• W3088798822 cites W2111935653 @default.
• W3088798822 cites W2112299196 @default.
• W3088798822 cites W2124290836 @default.
• W3088798822 cites W2126105956 @default.
• W3088798822 cites W2194775991 @default.
• W3088798822 cites W2295107390 @default.
• W3088798822 cites W2549139847 @default.
• W3088798822 cites W2606006859 @default.
• W3088798822 cites W2752782242 @default.
• W3088798822 cites W2796265726 @default.
• W3088798822 cites W2887063112 @default.
• W3088798822 cites W2953308748 @default.
• W3088798822 cites W2954070046 @default.
• W3088798822 cites W2954234207 @default.
• W3088798822 cites W2954826798 @default.
• W3088798822 cites W2960010704 @default.
• W3088798822 cites W2963125010 @default.
• W3088798822 cites W2963163009 @default.
• W3088798822 cites W2963446712 @default.
• W3088798822 cites W2963551763 @default.
• W3088798822 cites W2963821229 @default.
• W3088798822 cites W2964081807 @default.
• W3088798822 cites W2964166963 @default.
• W3088798822 cites W2965658867 @default.
• W3088798822 cites W2967733054 @default.
• W3088798822 cites W2981985696 @default.
• W3088798822 cites W3101156210 @default.
• W3088798822 cites W4255158661 @default.
• W3088798822 doi "https://doi.org/10.1109/tevc.2020.3024708" @default.
• W3088798822 hasPublicationYear "2021" @default.
• W3088798822 type Work @default.
• W3088798822 sameAs 3088798822 @default.
• W3088798822 citedByCount "74" @default.
• W3088798822 countsByYear W30887988222020 @default.
• W3088798822 countsByYear W30887988222021 @default.
• W3088798822 countsByYear W30887988222022 @default.
• W3088798822 countsByYear W30887988222023 @default.
• W3088798822 crossrefType "journal-article" @default.
• W3088798822 hasAuthorship W3088798822A5004837138 @default.
• W3088798822 hasAuthorship W3088798822A5027687139 @default.
• W3088798822 hasAuthorship W3088798822A5031717929 @default.
• W3088798822 hasAuthorship W3088798822A5033455019 @default.
• W3088798822 hasAuthorship W3088798822A5034853476 @default.
• W3088798822 hasAuthorship W3088798822A5068379698 @default.
• W3088798822 hasAuthorship W3088798822A5088394271 @default.
• W3088798822 hasBestOaLocation W30887988221 @default.
• W3088798822 hasConcept C105795698 @default.
• W3088798822 hasConcept C105902424 @default.
• W3088798822 hasConcept C108583219 @default.
• W3088798822 hasConcept C111919701 @default.
• W3088798822 hasConcept C115961682 @default.
• W3088798822 hasConcept C119857082 @default.
• W3088798822 hasConcept C13280743 @default.
• W3088798822 hasConcept C137635306 @default.
• W3088798822 hasConcept C154945302 @default.
• W3088798822 hasConcept C159149176 @default.
• W3088798822 hasConcept C162324750 @default.
• W3088798822 hasConcept C185798385 @default.
• W3088798822 hasConcept C193415008 @default.
• W3088798822 hasConcept C205649164 @default.
• W3088798822 hasConcept C21547014 @default.
• W3088798822 hasConcept C2778049539 @default.
• W3088798822 hasConcept C2780598303 @default.
• W3088798822 hasConcept C33923547 @default.
• W3088798822 hasConcept C38652104 @default.
• W3088798822 hasConcept C41008148 @default.
• W3088798822 hasConcept C50644808 @default.
• W3088798822 hasConcept C75294576 @default.
• W3088798822 hasConcept C81363708 @default.
• W3088798822 hasConcept C98045186 @default.
• W3088798822 hasConceptScore W3088798822C105795698 @default.
• W3088798822 hasConceptScore W3088798822C105902424 @default.
• W3088798822 hasConceptScore W3088798822C108583219 @default.
• W3088798822 hasConceptScore W3088798822C111919701 @default.
• W3088798822 hasConceptScore W3088798822C115961682 @default.
• W3088798822 hasConceptScore W3088798822C119857082 @default.
• W3088798822 hasConceptScore W3088798822C13280743 @default.
• W3088798822 hasConceptScore W3088798822C137635306 @default.
• W3088798822 hasConceptScore W3088798822C154945302 @default.
• W3088798822 hasConceptScore W3088798822C159149176 @default.
• W3088798822 hasConceptScore W3088798822C162324750 @default.

• next