Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319989134> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4319989134 abstract "As neural networks are increasingly included as core components of safety-critical systems, developing effective testing techniques specialized for them becomes crucial. The bulk of the research has focused on testing neural-network models; but these models are defined by writing programs, and there is growing evidence that these neural-network programs often have bugs too. This paper presents aNNoTest: an approach to generating test inputs for neural-network programs. A fundamental challenge is that the dynamically-typed languages (e.g., Python) commonly used to program neural networks cannot express detailed constraints about valid function inputs (e.g., matrices with certain dimensions). Without knowing these constraints, automated test-case generation is prone to producing invalid inputs, which trigger spurious failures and are useless for identifying real bugs. To address this problem, we introduce a simple annotation language tailored for concisely expressing valid function inputs in neural-network programs. aNNoTest takes as input an annotated program, and uses property-based testing to generate random inputs that satisfy the validity constraints. In the paper, we also outline guidelines that simplify writing aNNoTest annotations. We evaluated aNNoTest on 19 neural-network programs from Islam et al's survey., which we manually annotated following our guidelines -- producing 6 annotations per tested function on average. aNNoTest automatically generated test inputs that revealed 94 bugs, including 63 bugs that the survey reported for these projects. These results suggest that aNNoTest can be a valuable approach to finding widespread bugs in real-world neural-network programs." @default.
- W4319989134 created "2023-02-11" @default.
- W4319989134 creator A5031470846 @default.
- W4319989134 creator A5045819222 @default.
- W4319989134 date "2021-12-10" @default.
- W4319989134 modified "2023-09-28" @default.
- W4319989134 title "An Annotation-based Approach for Finding Bugs in Neural Network Programs" @default.
- W4319989134 doi "https://doi.org/10.48550/arxiv.2112.05567" @default.
- W4319989134 hasPublicationYear "2021" @default.
- W4319989134 type Work @default.
- W4319989134 citedByCount "0" @default.
- W4319989134 crossrefType "posted-content" @default.
- W4319989134 hasAuthorship W4319989134A5031470846 @default.
- W4319989134 hasAuthorship W4319989134A5045819222 @default.
- W4319989134 hasBestOaLocation W43199891341 @default.
- W4319989134 hasConcept C119857082 @default.
- W4319989134 hasConcept C124101348 @default.
- W4319989134 hasConcept C14036430 @default.
- W4319989134 hasConcept C154945302 @default.
- W4319989134 hasConcept C199360897 @default.
- W4319989134 hasConcept C2776321320 @default.
- W4319989134 hasConcept C41008148 @default.
- W4319989134 hasConcept C50644808 @default.
- W4319989134 hasConcept C519991488 @default.
- W4319989134 hasConcept C78458016 @default.
- W4319989134 hasConcept C86803240 @default.
- W4319989134 hasConcept C97256817 @default.
- W4319989134 hasConceptScore W4319989134C119857082 @default.
- W4319989134 hasConceptScore W4319989134C124101348 @default.
- W4319989134 hasConceptScore W4319989134C14036430 @default.
- W4319989134 hasConceptScore W4319989134C154945302 @default.
- W4319989134 hasConceptScore W4319989134C199360897 @default.
- W4319989134 hasConceptScore W4319989134C2776321320 @default.
- W4319989134 hasConceptScore W4319989134C41008148 @default.
- W4319989134 hasConceptScore W4319989134C50644808 @default.
- W4319989134 hasConceptScore W4319989134C519991488 @default.
- W4319989134 hasConceptScore W4319989134C78458016 @default.
- W4319989134 hasConceptScore W4319989134C86803240 @default.
- W4319989134 hasConceptScore W4319989134C97256817 @default.
- W4319989134 hasLocation W43199891341 @default.
- W4319989134 hasOpenAccess W4319989134 @default.
- W4319989134 hasPrimaryLocation W43199891341 @default.
- W4319989134 hasRelatedWork W2327204559 @default.
- W4319989134 hasRelatedWork W2529681551 @default.
- W4319989134 hasRelatedWork W2891993883 @default.
- W4319989134 hasRelatedWork W2909369566 @default.
- W4319989134 hasRelatedWork W3017187763 @default.
- W4319989134 hasRelatedWork W4232504361 @default.
- W4319989134 hasRelatedWork W4245752324 @default.
- W4319989134 hasRelatedWork W4285815787 @default.
- W4319989134 hasRelatedWork W4312949351 @default.
- W4319989134 hasRelatedWork W1629725936 @default.
- W4319989134 isParatext "false" @default.
- W4319989134 isRetracted "false" @default.
- W4319989134 workType "article" @default.