FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890590696> ?p ?o ?g. }

• W2890590696 abstract "Recent breakthroughs in Machine Learning (ML) applications, and especially in Deep Learning (DL), have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms (from mobile devices to datacenters) have resulted in a plethora of design challenges related to the constraints introduced by the hardware itself. &#x201C;What is the latency or energy cost for an inference made by a Deep Neural Network (DNN)?&#x201D; &#x201C;Is it possible to predict this latency or energy consumption before a model is even trained?&#x201D; &#x201C;If yes, how can machine learners take advantage of these models to design the hardware-optimal DNN for deployment?&#x201D; From lengthening battery life of mobile devices to reducing the runtime requirements of DL models executing in the cloud, the answers to these questions have drawn significant attention. One cannot optimize what isn&#x0027;t properly modeled. Therefore, it is important to understand the hardware efficiency of DL models during serving for making an inference, before even training the model. This key observation has motivated the use of predictive models to capture the hardware performance or energy efficiency of ML applications. Furthermore, ML practitioners are currently challenged with the task of designing the DNN model, i.e., of tuning the hyper-parameters of the DNN architecture, while optimizing for both accuracy of the DL model and its hardware efficiency. Therefore, state-of-the-art methodologies have proposed hardware-aware hyper-parameter optimization techniques. In this paper, we provide a comprehensive assessment of state-of-the-art work and selected results on the hardware-aware modeling and optimization for ML applications. We also highlight several open questions that are poised to give rise to novel hardware-aware designs in the next few years, as DL applications continue to significantly impact associated hardware systems and platforms." @default.
• W2890590696 created "2018-09-27" @default.
• W2890590696 creator A5022564890 @default.
• W2890590696 creator A5032077042 @default.
• W2890590696 creator A5040373050 @default.
• W2890590696 date "2018-11-05" @default.
• W2890590696 modified "2023-09-27" @default.
• W2890590696 title "Hardware-aware machine learning" @default.
• W2890590696 cites W2117539524 @default.
• W2890590696 cites W2192203593 @default.
• W2890590696 cites W2194775991 @default.
• W2890590696 cites W2289252105 @default.
• W2890590696 cites W2486475928 @default.
• W2890590696 cites W2538597346 @default.
• W2890590696 cites W2554302513 @default.
• W2890590696 cites W2605347906 @default.
• W2890590696 cites W2614392736 @default.
• W2890590696 cites W2742479298 @default.
• W2890590696 cites W2791845808 @default.
• W2890590696 cites W2808938483 @default.
• W2890590696 cites W2883929540 @default.
• W2890590696 cites W2963122961 @default.
• W2890590696 cites W2963240979 @default.
• W2890590696 cites W2964217527 @default.
• W2890590696 cites W4245199738 @default.
• W2890590696 doi "https://doi.org/10.1145/3240765.3243479" @default.
• W2890590696 hasPublicationYear "2018" @default.
• W2890590696 type Work @default.
• W2890590696 sameAs 2890590696 @default.
• W2890590696 citedByCount "31" @default.
• W2890590696 countsByYear W28905906962019 @default.
• W2890590696 countsByYear W28905906962020 @default.
• W2890590696 countsByYear W28905906962021 @default.
• W2890590696 countsByYear W28905906962022 @default.
• W2890590696 countsByYear W28905906962023 @default.
• W2890590696 crossrefType "proceedings-article" @default.
• W2890590696 hasAuthorship W2890590696A5022564890 @default.
• W2890590696 hasAuthorship W2890590696A5032077042 @default.
• W2890590696 hasAuthorship W2890590696A5040373050 @default.
• W2890590696 hasBestOaLocation W28905906961 @default.
• W2890590696 hasConcept C105339364 @default.
• W2890590696 hasConcept C108583219 @default.
• W2890590696 hasConcept C111919701 @default.
• W2890590696 hasConcept C113775141 @default.
• W2890590696 hasConcept C115903868 @default.
• W2890590696 hasConcept C118524514 @default.
• W2890590696 hasConcept C119599485 @default.
• W2890590696 hasConcept C119857082 @default.
• W2890590696 hasConcept C127413603 @default.
• W2890590696 hasConcept C149635348 @default.
• W2890590696 hasConcept C154945302 @default.
• W2890590696 hasConcept C186967261 @default.
• W2890590696 hasConcept C18903297 @default.
• W2890590696 hasConcept C26517878 @default.
• W2890590696 hasConcept C2742236 @default.
• W2890590696 hasConcept C2776214188 @default.
• W2890590696 hasConcept C2780165032 @default.
• W2890590696 hasConcept C41008148 @default.
• W2890590696 hasConcept C50644808 @default.
• W2890590696 hasConcept C76155785 @default.
• W2890590696 hasConcept C82876162 @default.
• W2890590696 hasConcept C86803240 @default.
• W2890590696 hasConcept C9390403 @default.
• W2890590696 hasConceptScore W2890590696C105339364 @default.
• W2890590696 hasConceptScore W2890590696C108583219 @default.
• W2890590696 hasConceptScore W2890590696C111919701 @default.
• W2890590696 hasConceptScore W2890590696C113775141 @default.
• W2890590696 hasConceptScore W2890590696C115903868 @default.
• W2890590696 hasConceptScore W2890590696C118524514 @default.
• W2890590696 hasConceptScore W2890590696C119599485 @default.
• W2890590696 hasConceptScore W2890590696C119857082 @default.
• W2890590696 hasConceptScore W2890590696C127413603 @default.
• W2890590696 hasConceptScore W2890590696C149635348 @default.
• W2890590696 hasConceptScore W2890590696C154945302 @default.
• W2890590696 hasConceptScore W2890590696C186967261 @default.
• W2890590696 hasConceptScore W2890590696C18903297 @default.
• W2890590696 hasConceptScore W2890590696C26517878 @default.
• W2890590696 hasConceptScore W2890590696C2742236 @default.
• W2890590696 hasConceptScore W2890590696C2776214188 @default.
• W2890590696 hasConceptScore W2890590696C2780165032 @default.
• W2890590696 hasConceptScore W2890590696C41008148 @default.
• W2890590696 hasConceptScore W2890590696C50644808 @default.
• W2890590696 hasConceptScore W2890590696C76155785 @default.
• W2890590696 hasConceptScore W2890590696C82876162 @default.
• W2890590696 hasConceptScore W2890590696C86803240 @default.
• W2890590696 hasConceptScore W2890590696C9390403 @default.
• W2890590696 hasFunder F4320306076 @default.
• W2890590696 hasLocation W28905906961 @default.
• W2890590696 hasOpenAccess W2890590696 @default.
• W2890590696 hasPrimaryLocation W28905906961 @default.
• W2890590696 hasRelatedWork W2608484494 @default.
• W2890590696 hasRelatedWork W2955669702 @default.
• W2890590696 hasRelatedWork W2963058055 @default.
• W2890590696 hasRelatedWork W2971714613 @default.
• W2890590696 hasRelatedWork W3006515133 @default.
• W2890590696 hasRelatedWork W3026174634 @default.
• W2890590696 hasRelatedWork W3195610113 @default.
• W2890590696 hasRelatedWork W4300865491 @default.
• W2890590696 hasRelatedWork W4321443870 @default.
• W2890590696 hasRelatedWork W4322776108 @default.

• next