Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385369637> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4385369637 endingPage "846" @default.
- W4385369637 startingPage "830" @default.
- W4385369637 abstract "Traffic forecasting is an important task for transportation engineering as it helps authorities to plan and control traffic flow, detect congestion, and reduce environmental impact. Deep learning techniques have gained traction in handling such complex datasets, but require expertise in neural architecture engineering, often beyond the scope of traffic management decision-makers. Our study aims to address this challenge by using neural architecture search (NAS) methods. These methods, which simplify neural architecture engineering by discovering task-specific neural architectures, are only recently applied to traffic prediction. We specifically focus on the performance estimation of neural architectures, a computationally demanding sub-problem of NAS, that often hinders the real-world application of these methods. Extending prior work on evolutionary NAS (ENAS), our work evaluates the utility of zero-cost (ZC) proxies, recently emerged cost-effective evaluators of network architectures. These proxies operate without necessitating training, thereby circumventing the computational bottleneck, albeit at a slight cost to accuracy. Our findings indicate that, when integrated into the ENAS framework, ZC proxies can accelerate the search process by two orders of magnitude at a small cost of accuracy. These results establish the viability of ZC proxies as a practical solution to accelerate NAS methods while maintaining model accuracy. Our research contributes to the domain by showcasing how ZC proxies can enhance the accessibility and usability of NAS methods for traffic forecasting, despite potential limitations in neural architecture engineering expertise. This novel approach significantly aids in the efficient application of deep learning techniques in real-world traffic management scenarios." @default.
- W4385369637 created "2023-07-29" @default.
- W4385369637 creator A5024184563 @default.
- W4385369637 creator A5080164322 @default.
- W4385369637 date "2023-07-28" @default.
- W4385369637 modified "2023-10-16" @default.
- W4385369637 title "Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting" @default.
- W4385369637 cites W2077537883 @default.
- W4385369637 cites W2082533141 @default.
- W4385369637 cites W2166901389 @default.
- W4385369637 cites W2572939427 @default.
- W4385369637 cites W2906154449 @default.
- W4385369637 cites W2914619357 @default.
- W4385369637 cites W2965341826 @default.
- W4385369637 cites W3008579601 @default.
- W4385369637 cites W3034723893 @default.
- W4385369637 cites W3034749137 @default.
- W4385369637 cites W3156351347 @default.
- W4385369637 cites W4235700536 @default.
- W4385369637 cites W4285325680 @default.
- W4385369637 cites W4294958479 @default.
- W4385369637 cites W4308086983 @default.
- W4385369637 cites W4360764821 @default.
- W4385369637 doi "https://doi.org/10.3390/make5030044" @default.
- W4385369637 hasPublicationYear "2023" @default.
- W4385369637 type Work @default.
- W4385369637 citedByCount "0" @default.
- W4385369637 crossrefType "journal-article" @default.
- W4385369637 hasAuthorship W4385369637A5024184563 @default.
- W4385369637 hasAuthorship W4385369637A5080164322 @default.
- W4385369637 hasBestOaLocation W43853696371 @default.
- W4385369637 hasConcept C107457646 @default.
- W4385369637 hasConcept C108583219 @default.
- W4385369637 hasConcept C111919701 @default.
- W4385369637 hasConcept C119857082 @default.
- W4385369637 hasConcept C123657996 @default.
- W4385369637 hasConcept C127413603 @default.
- W4385369637 hasConcept C142362112 @default.
- W4385369637 hasConcept C149635348 @default.
- W4385369637 hasConcept C153349607 @default.
- W4385369637 hasConcept C154945302 @default.
- W4385369637 hasConcept C170130773 @default.
- W4385369637 hasConcept C199360897 @default.
- W4385369637 hasConcept C201995342 @default.
- W4385369637 hasConcept C2778012447 @default.
- W4385369637 hasConcept C2780451532 @default.
- W4385369637 hasConcept C2780513914 @default.
- W4385369637 hasConcept C41008148 @default.
- W4385369637 hasConcept C50644808 @default.
- W4385369637 hasConcept C98045186 @default.
- W4385369637 hasConceptScore W4385369637C107457646 @default.
- W4385369637 hasConceptScore W4385369637C108583219 @default.
- W4385369637 hasConceptScore W4385369637C111919701 @default.
- W4385369637 hasConceptScore W4385369637C119857082 @default.
- W4385369637 hasConceptScore W4385369637C123657996 @default.
- W4385369637 hasConceptScore W4385369637C127413603 @default.
- W4385369637 hasConceptScore W4385369637C142362112 @default.
- W4385369637 hasConceptScore W4385369637C149635348 @default.
- W4385369637 hasConceptScore W4385369637C153349607 @default.
- W4385369637 hasConceptScore W4385369637C154945302 @default.
- W4385369637 hasConceptScore W4385369637C170130773 @default.
- W4385369637 hasConceptScore W4385369637C199360897 @default.
- W4385369637 hasConceptScore W4385369637C201995342 @default.
- W4385369637 hasConceptScore W4385369637C2778012447 @default.
- W4385369637 hasConceptScore W4385369637C2780451532 @default.
- W4385369637 hasConceptScore W4385369637C2780513914 @default.
- W4385369637 hasConceptScore W4385369637C41008148 @default.
- W4385369637 hasConceptScore W4385369637C50644808 @default.
- W4385369637 hasConceptScore W4385369637C98045186 @default.
- W4385369637 hasIssue "3" @default.
- W4385369637 hasLocation W43853696371 @default.
- W4385369637 hasOpenAccess W4385369637 @default.
- W4385369637 hasPrimaryLocation W43853696371 @default.
- W4385369637 hasRelatedWork W3014300295 @default.
- W4385369637 hasRelatedWork W3164822677 @default.
- W4385369637 hasRelatedWork W4223943233 @default.
- W4385369637 hasRelatedWork W4225161397 @default.
- W4385369637 hasRelatedWork W4309045103 @default.
- W4385369637 hasRelatedWork W4312200629 @default.
- W4385369637 hasRelatedWork W4360585206 @default.
- W4385369637 hasRelatedWork W4364306694 @default.
- W4385369637 hasRelatedWork W4380075502 @default.
- W4385369637 hasRelatedWork W4380086463 @default.
- W4385369637 hasVolume "5" @default.
- W4385369637 isParatext "false" @default.
- W4385369637 isRetracted "false" @default.
- W4385369637 workType "article" @default.