Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200693768> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3200693768 abstract "With the advances in hardware technologies, embedded and Edge devices are now able to offer sufficient memory and computational power to accommodate light-weight machine-learning (ML) classifiers. However, due to the intensive code optimization and summarization in the design phase, the reliability of light-weight ML applications is at risk. In this paper, we study the reliability of three prototypical light-weight ML applications against the well-known control flow (CF) errors. We have injected a total of 66,156 CF errors into Bonsai, ProtoNN, and TensorFlow Lite ML applications running on the Arduino board. Based on the results obtained from the error-injections, we found that CF errors could affect either the functionality or the classification accuracy of the ML-based inference as the embedded application. We conclude that making a single decision only after a long sequence of computations/branches may be more error-prone. This issue can be addressed by combining the inferences of intermediate nodes in the chain to obtain the final classification decision." @default.
- W3200693768 created "2021-09-27" @default.
- W3200693768 creator A5004529123 @default.
- W3200693768 creator A5049468839 @default.
- W3200693768 creator A5075935061 @default.
- W3200693768 date "2021-08-09" @default.
- W3200693768 modified "2023-09-23" @default.
- W3200693768 title "Reliability Assessment of Tiny Machine Learning Algorithms in the Presence of Control Flow Errors" @default.
- W3200693768 cites W1965936844 @default.
- W3200693768 cites W2106525823 @default.
- W3200693768 cites W2402144811 @default.
- W3200693768 cites W2732039841 @default.
- W3200693768 cites W2732951378 @default.
- W3200693768 cites W2919115771 @default.
- W3200693768 cites W3026905253 @default.
- W3200693768 cites W3067862503 @default.
- W3200693768 cites W3083587321 @default.
- W3200693768 doi "https://doi.org/10.1109/mwscas47672.2021.9531793" @default.
- W3200693768 hasPublicationYear "2021" @default.
- W3200693768 type Work @default.
- W3200693768 sameAs 3200693768 @default.
- W3200693768 citedByCount "0" @default.
- W3200693768 crossrefType "proceedings-article" @default.
- W3200693768 hasAuthorship W3200693768A5004529123 @default.
- W3200693768 hasAuthorship W3200693768A5049468839 @default.
- W3200693768 hasAuthorship W3200693768A5075935061 @default.
- W3200693768 hasConcept C103088060 @default.
- W3200693768 hasConcept C113775141 @default.
- W3200693768 hasConcept C11413529 @default.
- W3200693768 hasConcept C119857082 @default.
- W3200693768 hasConcept C121332964 @default.
- W3200693768 hasConcept C127413603 @default.
- W3200693768 hasConcept C154945302 @default.
- W3200693768 hasConcept C163258240 @default.
- W3200693768 hasConcept C170858558 @default.
- W3200693768 hasConcept C200601418 @default.
- W3200693768 hasConcept C2776214188 @default.
- W3200693768 hasConcept C41008148 @default.
- W3200693768 hasConcept C43214815 @default.
- W3200693768 hasConcept C62520636 @default.
- W3200693768 hasConceptScore W3200693768C103088060 @default.
- W3200693768 hasConceptScore W3200693768C113775141 @default.
- W3200693768 hasConceptScore W3200693768C11413529 @default.
- W3200693768 hasConceptScore W3200693768C119857082 @default.
- W3200693768 hasConceptScore W3200693768C121332964 @default.
- W3200693768 hasConceptScore W3200693768C127413603 @default.
- W3200693768 hasConceptScore W3200693768C154945302 @default.
- W3200693768 hasConceptScore W3200693768C163258240 @default.
- W3200693768 hasConceptScore W3200693768C170858558 @default.
- W3200693768 hasConceptScore W3200693768C200601418 @default.
- W3200693768 hasConceptScore W3200693768C2776214188 @default.
- W3200693768 hasConceptScore W3200693768C41008148 @default.
- W3200693768 hasConceptScore W3200693768C43214815 @default.
- W3200693768 hasConceptScore W3200693768C62520636 @default.
- W3200693768 hasLocation W32006937681 @default.
- W3200693768 hasOpenAccess W3200693768 @default.
- W3200693768 hasPrimaryLocation W32006937681 @default.
- W3200693768 hasRelatedWork W1992148151 @default.
- W3200693768 hasRelatedWork W2073680493 @default.
- W3200693768 hasRelatedWork W2075934899 @default.
- W3200693768 hasRelatedWork W2353470484 @default.
- W3200693768 hasRelatedWork W2355501997 @default.
- W3200693768 hasRelatedWork W2359614193 @default.
- W3200693768 hasRelatedWork W2365083683 @default.
- W3200693768 hasRelatedWork W2367319755 @default.
- W3200693768 hasRelatedWork W2373895031 @default.
- W3200693768 hasRelatedWork W2963058055 @default.
- W3200693768 isParatext "false" @default.
- W3200693768 isRetracted "false" @default.
- W3200693768 magId "3200693768" @default.
- W3200693768 workType "article" @default.