Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287553497> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4287553497 abstract "Today, Deep Learning (DL) enhances almost every industrial sector, including safety-critical areas. The next generation of safety standards will define appropriate verification techniques for DL-based applications and propose adequate fault tolerance mechanisms. DL-based applications, like any other software, are susceptible to common random hardware faults such as bit flips, which occur in RAM and CPU registers. Such faults can lead to silent data corruption. Therefore, it is crucial to develop methods and tools that help to evaluate how DL components operate under the presence of such faults. In this paper, we introduce two new Fault Injection (FI) frameworks InjectTF and InjectTF2 for TensorFlow 1 and TensorFlow 2, respectively. Both frameworks are available on GitHub and allow the configurable injection of random faults into Neural Networks (NN). In order to demonstrate the feasibility of the frameworks, we also present the results of FI experiments conducted on four VGG-based Convolutional NNs using two image sets. The results demonstrate how random bit flips in the output of particular mathematical operations and layers of NNs affect the classification accuracy. These results help to identify the most critical operations and layers, compare the reliability characteristics of functionally similar NNs, and introduce selective fault tolerance mechanisms." @default.
- W4287553497 created "2022-07-25" @default.
- W4287553497 creator A5010821573 @default.
- W4287553497 creator A5022623174 @default.
- W4287553497 creator A5042050845 @default.
- W4287553497 creator A5058561926 @default.
- W4287553497 creator A5066899205 @default.
- W4287553497 creator A5069435273 @default.
- W4287553497 creator A5088230065 @default.
- W4287553497 date "2020-12-13" @default.
- W4287553497 modified "2023-10-15" @default.
- W4287553497 title "Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs" @default.
- W4287553497 doi "https://doi.org/10.48550/arxiv.2012.07037" @default.
- W4287553497 hasPublicationYear "2020" @default.
- W4287553497 type Work @default.
- W4287553497 citedByCount "0" @default.
- W4287553497 crossrefType "posted-content" @default.
- W4287553497 hasAuthorship W4287553497A5010821573 @default.
- W4287553497 hasAuthorship W4287553497A5022623174 @default.
- W4287553497 hasAuthorship W4287553497A5042050845 @default.
- W4287553497 hasAuthorship W4287553497A5058561926 @default.
- W4287553497 hasAuthorship W4287553497A5066899205 @default.
- W4287553497 hasAuthorship W4287553497A5069435273 @default.
- W4287553497 hasAuthorship W4287553497A5088230065 @default.
- W4287553497 hasBestOaLocation W42875534971 @default.
- W4287553497 hasConcept C108583219 @default.
- W4287553497 hasConcept C113775141 @default.
- W4287553497 hasConcept C119857082 @default.
- W4287553497 hasConcept C120314980 @default.
- W4287553497 hasConcept C121332964 @default.
- W4287553497 hasConcept C127313418 @default.
- W4287553497 hasConcept C149635348 @default.
- W4287553497 hasConcept C154945302 @default.
- W4287553497 hasConcept C163258240 @default.
- W4287553497 hasConcept C165205528 @default.
- W4287553497 hasConcept C175551986 @default.
- W4287553497 hasConcept C199360897 @default.
- W4287553497 hasConcept C2775928411 @default.
- W4287553497 hasConcept C2777904410 @default.
- W4287553497 hasConcept C41008148 @default.
- W4287553497 hasConcept C43214815 @default.
- W4287553497 hasConcept C50644808 @default.
- W4287553497 hasConcept C62520636 @default.
- W4287553497 hasConcept C63540848 @default.
- W4287553497 hasConcept C81363708 @default.
- W4287553497 hasConceptScore W4287553497C108583219 @default.
- W4287553497 hasConceptScore W4287553497C113775141 @default.
- W4287553497 hasConceptScore W4287553497C119857082 @default.
- W4287553497 hasConceptScore W4287553497C120314980 @default.
- W4287553497 hasConceptScore W4287553497C121332964 @default.
- W4287553497 hasConceptScore W4287553497C127313418 @default.
- W4287553497 hasConceptScore W4287553497C149635348 @default.
- W4287553497 hasConceptScore W4287553497C154945302 @default.
- W4287553497 hasConceptScore W4287553497C163258240 @default.
- W4287553497 hasConceptScore W4287553497C165205528 @default.
- W4287553497 hasConceptScore W4287553497C175551986 @default.
- W4287553497 hasConceptScore W4287553497C199360897 @default.
- W4287553497 hasConceptScore W4287553497C2775928411 @default.
- W4287553497 hasConceptScore W4287553497C2777904410 @default.
- W4287553497 hasConceptScore W4287553497C41008148 @default.
- W4287553497 hasConceptScore W4287553497C43214815 @default.
- W4287553497 hasConceptScore W4287553497C50644808 @default.
- W4287553497 hasConceptScore W4287553497C62520636 @default.
- W4287553497 hasConceptScore W4287553497C63540848 @default.
- W4287553497 hasConceptScore W4287553497C81363708 @default.
- W4287553497 hasLocation W42875534971 @default.
- W4287553497 hasOpenAccess W4287553497 @default.
- W4287553497 hasPrimaryLocation W42875534971 @default.
- W4287553497 hasRelatedWork W10122466 @default.
- W4287553497 hasRelatedWork W10297536 @default.
- W4287553497 hasRelatedWork W1193270 @default.
- W4287553497 hasRelatedWork W13525404 @default.
- W4287553497 hasRelatedWork W1362903 @default.
- W4287553497 hasRelatedWork W14117024 @default.
- W4287553497 hasRelatedWork W286938 @default.
- W4287553497 hasRelatedWork W5317949 @default.
- W4287553497 hasRelatedWork W6997194 @default.
- W4287553497 hasRelatedWork W9190101 @default.
- W4287553497 isParatext "false" @default.
- W4287553497 isRetracted "false" @default.
- W4287553497 workType "article" @default.