Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313563684> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4313563684 abstract "Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are being used on resource-constrained embedded devices. We observe that, similar to traditional software, redundant computation exists in AdNNs, resulting in considerable performance degradation. The performance degradation is dependent on the input and is referred to as input-dependent performance bottlenecks (IDPBs). To ensure an AdNN satisfies the performance requirements of resource-constrained applications, it is essential to conduct performance testing to detect IDPBs in the AdNN. Existing neural network testing methods are primarily concerned with correctness testing, which does not involve performance testing. To fill this gap, we propose DeepPerform, a scalable approach to generate test samples to detect the IDPBs in AdNNs. We first demonstrate how the problem of generating performance test samples detecting IDPBs can be formulated as an optimization problem. Following that, we demonstrate how DeepPerform efficiently handles the optimization problem by learning and estimating the distribution of AdNNs’ computational consumption. We evaluate DeepPerform on three widely used datasets against five popular AdNN models. The results show that DeepPerform generates test samples that cause more severe performance degradation (FLOPs: increase up to 552%). Furthermore, DeepPerform is substantially more efficient than the baseline methods in generating test inputs (runtime overhead: only 6–10 milliseconds)." @default.
- W4313563684 created "2023-01-06" @default.
- W4313563684 creator A5001457257 @default.
- W4313563684 creator A5009590736 @default.
- W4313563684 creator A5016858094 @default.
- W4313563684 creator A5054453413 @default.
- W4313563684 date "2022-10-10" @default.
- W4313563684 modified "2023-10-13" @default.
- W4313563684 title "DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks" @default.
- W4313563684 cites W2034978228 @default.
- W4313563684 cites W2065325279 @default.
- W4313563684 cites W2159586681 @default.
- W4313563684 cites W2327501763 @default.
- W4313563684 cites W2616028256 @default.
- W4313563684 cites W2752340395 @default.
- W4313563684 cites W2799176631 @default.
- W4313563684 cites W2803831897 @default.
- W4313563684 cites W2865298191 @default.
- W4313563684 cites W2884751099 @default.
- W4313563684 cites W2888307014 @default.
- W4313563684 cites W2909146762 @default.
- W4313563684 cites W2962677625 @default.
- W4313563684 cites W2962935523 @default.
- W4313563684 cites W2962944050 @default.
- W4313563684 cites W2963327228 @default.
- W4313563684 cites W2963393494 @default.
- W4313563684 cites W2963969878 @default.
- W4313563684 cites W3090608524 @default.
- W4313563684 cites W3091441586 @default.
- W4313563684 cites W3099444373 @default.
- W4313563684 cites W3144271226 @default.
- W4313563684 cites W3191321386 @default.
- W4313563684 cites W4312648739 @default.
- W4313563684 doi "https://doi.org/10.1145/3551349.3561158" @default.
- W4313563684 hasPublicationYear "2022" @default.
- W4313563684 type Work @default.
- W4313563684 citedByCount "3" @default.
- W4313563684 countsByYear W43135636842023 @default.
- W4313563684 crossrefType "proceedings-article" @default.
- W4313563684 hasAuthorship W4313563684A5001457257 @default.
- W4313563684 hasAuthorship W4313563684A5009590736 @default.
- W4313563684 hasAuthorship W4313563684A5016858094 @default.
- W4313563684 hasAuthorship W4313563684A5054453413 @default.
- W4313563684 hasBestOaLocation W43135636841 @default.
- W4313563684 hasConcept C111919701 @default.
- W4313563684 hasConcept C113775141 @default.
- W4313563684 hasConcept C11413529 @default.
- W4313563684 hasConcept C119857082 @default.
- W4313563684 hasConcept C120314980 @default.
- W4313563684 hasConcept C2779960059 @default.
- W4313563684 hasConcept C41008148 @default.
- W4313563684 hasConcept C48044578 @default.
- W4313563684 hasConcept C50644808 @default.
- W4313563684 hasConcept C55439883 @default.
- W4313563684 hasConcept C77088390 @default.
- W4313563684 hasConceptScore W4313563684C111919701 @default.
- W4313563684 hasConceptScore W4313563684C113775141 @default.
- W4313563684 hasConceptScore W4313563684C11413529 @default.
- W4313563684 hasConceptScore W4313563684C119857082 @default.
- W4313563684 hasConceptScore W4313563684C120314980 @default.
- W4313563684 hasConceptScore W4313563684C2779960059 @default.
- W4313563684 hasConceptScore W4313563684C41008148 @default.
- W4313563684 hasConceptScore W4313563684C48044578 @default.
- W4313563684 hasConceptScore W4313563684C50644808 @default.
- W4313563684 hasConceptScore W4313563684C55439883 @default.
- W4313563684 hasConceptScore W4313563684C77088390 @default.
- W4313563684 hasLocation W43135636841 @default.
- W4313563684 hasLocation W43135636842 @default.
- W4313563684 hasOpenAccess W4313563684 @default.
- W4313563684 hasPrimaryLocation W43135636841 @default.
- W4313563684 hasRelatedWork W1498391134 @default.
- W4313563684 hasRelatedWork W1596201972 @default.
- W4313563684 hasRelatedWork W1605167062 @default.
- W4313563684 hasRelatedWork W1967954938 @default.
- W4313563684 hasRelatedWork W1986253068 @default.
- W4313563684 hasRelatedWork W2064105003 @default.
- W4313563684 hasRelatedWork W2364921833 @default.
- W4313563684 hasRelatedWork W2380023786 @default.
- W4313563684 hasRelatedWork W2385146268 @default.
- W4313563684 hasRelatedWork W94000989 @default.
- W4313563684 isParatext "false" @default.
- W4313563684 isRetracted "false" @default.
- W4313563684 workType "article" @default.