FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137606981> ?p ?o ?g. }

• W3137606981 endingPage "1" @default.
• W3137606981 startingPage "1" @default.
• W3137606981 abstract "Pattern-recognition algorithms from machine learning play a prominent role in embedded sensing systems to derive inferences from sensor data. Very often, such systems face severe energy constraints, especially when dealing with high-dimensional data, such as images. The focus of this study is on reducing computational energy by exploiting the concept of transfer learning and energy-efficient dataflow accelerators. We show that the use of convolutional autoencoders can enable various opportunities to reduce computational energy and avoid significant reduction in inference performance when multiple task categories are targeted for inference. We validate our approach through a multi-task case study. The study targets a set of pictures with each picture containing four different task categories: gender, smile, glasses, and pose. In order to minimize inference time and computational energy, a convolutional autoencoder is used for learning a generalized representation of the images. Three scenarios are analyzed: transferring layers using convolutional autoencoders, transferring layers using convolutional neural networks trained on different tasks, and no layer transfer. We show that when the convolutional layers with one fully-connected layer are transferred using convolutional autoencoders, we can achieve a reduction of <inline-formula><tex-math notation=LaTeX>$6.58times$</tex-math></inline-formula> in computational energy, while improving performance by 1.98, 1.88, 4.11, and 1.47 percent for gender, smile, glasses, and pose inferences, respectively, as compared to the no-transfer method, when the number of training samples is small." @default.
• W3137606981 created "2021-03-29" @default.
• W3137606981 creator A5018159956 @default.
• W3137606981 creator A5036267240 @default.
• W3137606981 creator A5086131079 @default.
• W3137606981 date "2021-01-01" @default.
• W3137606981 modified "2023-09-30" @default.
• W3137606981 title "Convolutional Autoencoder-Based Transfer Learning for Multi-Task Image Inferences" @default.
• W3137606981 cites W1546200464 @default.
• W3137606981 cites W1583031633 @default.
• W3137606981 cites W1722318740 @default.
• W3137606981 cites W1896424170 @default.
• W3137606981 cites W1964471912 @default.
• W3137606981 cites W1998808035 @default.
• W3137606981 cites W1999085092 @default.
• W3137606981 cites W2009832130 @default.
• W3137606981 cites W2013305145 @default.
• W3137606981 cites W2022508996 @default.
• W3137606981 cites W2025768430 @default.
• W3137606981 cites W2053757129 @default.
• W3137606981 cites W2067523571 @default.
• W3137606981 cites W2094756095 @default.
• W3137606981 cites W2100495367 @default.
• W3137606981 cites W2112796928 @default.
• W3137606981 cites W2116064496 @default.
• W3137606981 cites W2122156965 @default.
• W3137606981 cites W2161381512 @default.
• W3137606981 cites W2163922914 @default.
• W3137606981 cites W2165698076 @default.
• W3137606981 cites W2166694921 @default.
• W3137606981 cites W2288807527 @default.
• W3137606981 cites W2321627895 @default.
• W3137606981 cites W2338271170 @default.
• W3137606981 cites W2394599079 @default.
• W3137606981 cites W2442974303 @default.
• W3137606981 cites W2554302513 @default.
• W3137606981 cites W2565358069 @default.
• W3137606981 cites W2592224809 @default.
• W3137606981 cites W2604319603 @default.
• W3137606981 cites W2666784499 @default.
• W3137606981 cites W2752788177 @default.
• W3137606981 cites W2804196292 @default.
• W3137606981 doi "https://doi.org/10.1109/tetc.2021.3068063" @default.
• W3137606981 hasPublicationYear "2021" @default.
• W3137606981 type Work @default.
• W3137606981 sameAs 3137606981 @default.
• W3137606981 citedByCount "7" @default.
• W3137606981 countsByYear W31376069812022 @default.
• W3137606981 countsByYear W31376069812023 @default.
• W3137606981 crossrefType "journal-article" @default.
• W3137606981 hasAuthorship W3137606981A5018159956 @default.
• W3137606981 hasAuthorship W3137606981A5036267240 @default.
• W3137606981 hasAuthorship W3137606981A5086131079 @default.
• W3137606981 hasConcept C101738243 @default.
• W3137606981 hasConcept C105795698 @default.
• W3137606981 hasConcept C108583219 @default.
• W3137606981 hasConcept C111335779 @default.
• W3137606981 hasConcept C119857082 @default.
• W3137606981 hasConcept C150899416 @default.
• W3137606981 hasConcept C153180895 @default.
• W3137606981 hasConcept C154945302 @default.
• W3137606981 hasConcept C162324750 @default.
• W3137606981 hasConcept C186370098 @default.
• W3137606981 hasConcept C187736073 @default.
• W3137606981 hasConcept C2524010 @default.
• W3137606981 hasConcept C2776214188 @default.
• W3137606981 hasConcept C2780451532 @default.
• W3137606981 hasConcept C33923547 @default.
• W3137606981 hasConcept C41008148 @default.
• W3137606981 hasConcept C81363708 @default.
• W3137606981 hasConceptScore W3137606981C101738243 @default.
• W3137606981 hasConceptScore W3137606981C105795698 @default.
• W3137606981 hasConceptScore W3137606981C108583219 @default.
• W3137606981 hasConceptScore W3137606981C111335779 @default.
• W3137606981 hasConceptScore W3137606981C119857082 @default.
• W3137606981 hasConceptScore W3137606981C150899416 @default.
• W3137606981 hasConceptScore W3137606981C153180895 @default.
• W3137606981 hasConceptScore W3137606981C154945302 @default.
• W3137606981 hasConceptScore W3137606981C162324750 @default.
• W3137606981 hasConceptScore W3137606981C186370098 @default.
• W3137606981 hasConceptScore W3137606981C187736073 @default.
• W3137606981 hasConceptScore W3137606981C2524010 @default.
• W3137606981 hasConceptScore W3137606981C2776214188 @default.
• W3137606981 hasConceptScore W3137606981C2780451532 @default.
• W3137606981 hasConceptScore W3137606981C33923547 @default.
• W3137606981 hasConceptScore W3137606981C41008148 @default.
• W3137606981 hasConceptScore W3137606981C81363708 @default.
• W3137606981 hasFunder F4320306076 @default.
• W3137606981 hasLocation W31376069811 @default.
• W3137606981 hasOpenAccess W3137606981 @default.
• W3137606981 hasPrimaryLocation W31376069811 @default.
• W3137606981 hasRelatedWork W3018421652 @default.
• W3137606981 hasRelatedWork W3021430260 @default.
• W3137606981 hasRelatedWork W3091976719 @default.
• W3137606981 hasRelatedWork W3192840557 @default.
• W3137606981 hasRelatedWork W4220996320 @default.
• W3137606981 hasRelatedWork W4224044423 @default.
• W3137606981 hasRelatedWork W4285149559 @default.

• next