FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310147199> ?p ?o ?g. }

• W4310147199 endingPage "170" @default.
• W4310147199 startingPage "152" @default.
• W4310147199 abstract "The state-of-the-art performance for several real-world problems is currently reached by deep and, in particular, convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, leading to highly performing, yet very large neural networks with typically millions to billions of parameters. As a result, such models are often redundant and excessively oversized, with a detrimental effect on the environment in terms of unnecessary energy consumption and a limitation to their deployment on low-resource devices. The necessity for compression techniques able to reduce the number of model parameters and their resource demand is thereby increasingly felt by the research community. In this paper we propose the first extensive comparison, to the best of our knowledge, of the main lossy and structure-preserving approaches to compress pre-trained CNNs, applicable in principle to any existing model. Our study is intended to provide a first and preliminary guidance to choose the most suitable compression technique when there is the need to reduce the occupancy of pre-trained models. Both convolutional and fully-connected layers are included in the analysis. Our experiments involved two pre-trained state-of-the-art CNNs (proposed to solve classification or regression problems) and five benchmarks, and gave rise to important insights about the applicability and performance of such techniques w.r.t. the type of layer to be compressed and the category of problem tackled." @default.
• W4310147199 created "2022-11-30" @default.
• W4310147199 creator A5005837237 @default.
• W4310147199 creator A5026141403 @default.
• W4310147199 creator A5042201502 @default.
• W4310147199 creator A5075385368 @default.
• W4310147199 date "2023-02-01" @default.
• W4310147199 modified "2023-10-18" @default.
• W4310147199 title "Deep neural networks compression: A comparative survey and choice recommendations" @default.
• W4310147199 cites W1524097605 @default.
• W4310147199 cites W1971259134 @default.
• W4310147199 cites W1989881099 @default.
• W4310147199 cites W2001381117 @default.
• W4310147199 cites W2032893592 @default.
• W4310147199 cites W2035585923 @default.
• W4310147199 cites W2058641082 @default.
• W4310147199 cites W2086286404 @default.
• W4310147199 cites W2112796928 @default.
• W4310147199 cites W2121775913 @default.
• W4310147199 cites W2131578006 @default.
• W4310147199 cites W2146519989 @default.
• W4310147199 cites W2165698076 @default.
• W4310147199 cites W2294543795 @default.
• W4310147199 cites W2754084392 @default.
• W4310147199 cites W2785947426 @default.
• W4310147199 cites W2883111419 @default.
• W4310147199 cites W2906408823 @default.
• W4310147199 cites W2962761403 @default.
• W4310147199 cites W2962939807 @default.
• W4310147199 cites W2963072899 @default.
• W4310147199 cites W2963122961 @default.
• W4310147199 cites W2963163009 @default.
• W4310147199 cites W2963363373 @default.
• W4310147199 cites W2965862774 @default.
• W4310147199 cites W3006631416 @default.
• W4310147199 cites W3008725350 @default.
• W4310147199 cites W3012561096 @default.
• W4310147199 cites W3018835489 @default.
• W4310147199 cites W3111732345 @default.
• W4310147199 cites W3209732473 @default.
• W4310147199 doi "https://doi.org/10.1016/j.neucom.2022.11.072" @default.
• W4310147199 hasPublicationYear "2023" @default.
• W4310147199 type Work @default.
• W4310147199 citedByCount "11" @default.
• W4310147199 countsByYear W43101471992023 @default.
• W4310147199 crossrefType "journal-article" @default.
• W4310147199 hasAuthorship W4310147199A5005837237 @default.
• W4310147199 hasAuthorship W4310147199A5026141403 @default.
• W4310147199 hasAuthorship W4310147199A5042201502 @default.
• W4310147199 hasAuthorship W4310147199A5075385368 @default.
• W4310147199 hasBestOaLocation W43101471991 @default.
• W4310147199 hasConcept C105339364 @default.
• W4310147199 hasConcept C108583219 @default.
• W4310147199 hasConcept C115903868 @default.
• W4310147199 hasConcept C119857082 @default.
• W4310147199 hasConcept C124101348 @default.
• W4310147199 hasConcept C154945302 @default.
• W4310147199 hasConcept C165021410 @default.
• W4310147199 hasConcept C165696696 @default.
• W4310147199 hasConcept C18903297 @default.
• W4310147199 hasConcept C202444582 @default.
• W4310147199 hasConcept C206345919 @default.
• W4310147199 hasConcept C2780165032 @default.
• W4310147199 hasConcept C2984842247 @default.
• W4310147199 hasConcept C31258907 @default.
• W4310147199 hasConcept C33923547 @default.
• W4310147199 hasConcept C38652104 @default.
• W4310147199 hasConcept C41008148 @default.
• W4310147199 hasConcept C50644808 @default.
• W4310147199 hasConcept C81363708 @default.
• W4310147199 hasConcept C86803240 @default.
• W4310147199 hasConcept C9652623 @default.
• W4310147199 hasConceptScore W4310147199C105339364 @default.
• W4310147199 hasConceptScore W4310147199C108583219 @default.
• W4310147199 hasConceptScore W4310147199C115903868 @default.
• W4310147199 hasConceptScore W4310147199C119857082 @default.
• W4310147199 hasConceptScore W4310147199C124101348 @default.
• W4310147199 hasConceptScore W4310147199C154945302 @default.
• W4310147199 hasConceptScore W4310147199C165021410 @default.
• W4310147199 hasConceptScore W4310147199C165696696 @default.
• W4310147199 hasConceptScore W4310147199C18903297 @default.
• W4310147199 hasConceptScore W4310147199C202444582 @default.
• W4310147199 hasConceptScore W4310147199C206345919 @default.
• W4310147199 hasConceptScore W4310147199C2780165032 @default.
• W4310147199 hasConceptScore W4310147199C2984842247 @default.
• W4310147199 hasConceptScore W4310147199C31258907 @default.
• W4310147199 hasConceptScore W4310147199C33923547 @default.
• W4310147199 hasConceptScore W4310147199C38652104 @default.
• W4310147199 hasConceptScore W4310147199C41008148 @default.
• W4310147199 hasConceptScore W4310147199C50644808 @default.
• W4310147199 hasConceptScore W4310147199C81363708 @default.
• W4310147199 hasConceptScore W4310147199C86803240 @default.
• W4310147199 hasConceptScore W4310147199C9652623 @default.
• W4310147199 hasFunder F4320321873 @default.
• W4310147199 hasLocation W43101471991 @default.
• W4310147199 hasLocation W43101471992 @default.
• W4310147199 hasOpenAccess W4310147199 @default.
• W4310147199 hasPrimaryLocation W43101471991 @default.

• next