Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161666929> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3161666929 abstract "Nowadays, we are witnessing an increasing demand in both corporates and academia for exploiting Deep Learning (DL) to solve complex real-world problems. A DL program encodes the network structure of a desirable DL model and the process by which the model learns from the training dataset. Like any software, a DL program can be faulty, which implies substantial challenges of software quality assurance, especially in safety-critical domains. It is therefore crucial to equip DL development teams with efficient fault detection techniques and tools. In this paper, we propose NeuraLint, a model-based fault detection approach for DL programs, using meta-modelling and graph transformations. First, we design a meta-model for DL programs that includes their base skeleton and fundamental properties. Then, we construct a graph-based verification process that covers 23 rules defined on top of the meta-model and implemented as graph transformations to detect faults and design inefficiencies in the generated models (i.e., instances of the meta-model). First, the proposed approach is evaluated by finding faults and design inefficiencies in 28 synthesized examples built from common problems reported in the literature. Then NeuraLint successfully finds 64 faults and design inefficiencies in 34 real-world DL programs extracted from Stack Overflow posts and GitHub repositories. The results show that NeuraLint effectively detects faults and design issues in both synthesized and real-world examples with a recall of 70.5 % and a precision of 100 %. Although the proposed meta-model is designed for feedforward neural networks, it can be extended to support other neural network architectures such as recurrent neural networks. Researchers can also expand our set of verification rules to cover more types of issues in DL programs." @default.
- W3161666929 created "2021-05-24" @default.
- W3161666929 creator A5048134538 @default.
- W3161666929 creator A5071052367 @default.
- W3161666929 creator A5079607563 @default.
- W3161666929 creator A5091616184 @default.
- W3161666929 date "2021-01-01" @default.
- W3161666929 modified "2023-10-14" @default.
- W3161666929 title "Automatic Fault Detection for Deep Learning Programs Using Graph Transformations" @default.
- W3161666929 cites W1523493493 @default.
- W3161666929 cites W1533861849 @default.
- W3161666929 cites W1563795667 @default.
- W3161666929 cites W1686810756 @default.
- W3161666929 cites W1836465849 @default.
- W3161666929 cites W1861492603 @default.
- W3161666929 cites W1932847118 @default.
- W3161666929 cites W1978660636 @default.
- W3161666929 cites W1998371662 @default.
- W3161666929 cites W2095705004 @default.
- W3161666929 cites W2108598243 @default.
- W3161666929 cites W2112796928 @default.
- W3161666929 cites W2123045220 @default.
- W3161666929 cites W2131966463 @default.
- W3161666929 cites W2157901438 @default.
- W3161666929 cites W2163605009 @default.
- W3161666929 cites W2183341477 @default.
- W3161666929 cites W2194775991 @default.
- W3161666929 cites W2279098554 @default.
- W3161666929 cites W2418033038 @default.
- W3161666929 cites W2419597278 @default.
- W3161666929 cites W2546781373 @default.
- W3161666929 cites W2557283755 @default.
- W3161666929 cites W2616028256 @default.
- W3161666929 cites W2788658682 @default.
- W3161666929 cites W2850992922 @default.
- W3161666929 cites W2859484040 @default.
- W3161666929 cites W2899675781 @default.
- W3161666929 cites W2917668703 @default.
- W3161666929 cites W2962734576 @default.
- W3161666929 cites W2962971773 @default.
- W3161666929 cites W2963499994 @default.
- W3161666929 cites W2963808954 @default.
- W3161666929 cites W2968594320 @default.
- W3161666929 cites W2978190445 @default.
- W3161666929 cites W2989575070 @default.
- W3161666929 cites W2994150880 @default.
- W3161666929 cites W2996248296 @default.
- W3161666929 cites W3004493192 @default.
- W3161666929 cites W3005940936 @default.
- W3161666929 cites W3015119114 @default.
- W3161666929 cites W3090643686 @default.
- W3161666929 cites W3091633490 @default.
- W3161666929 hasPublicationYear "2021" @default.
- W3161666929 type Work @default.
- W3161666929 sameAs 3161666929 @default.
- W3161666929 citedByCount "0" @default.
- W3161666929 crossrefType "journal-article" @default.
- W3161666929 hasAuthorship W3161666929A5048134538 @default.
- W3161666929 hasAuthorship W3161666929A5071052367 @default.
- W3161666929 hasAuthorship W3161666929A5079607563 @default.
- W3161666929 hasAuthorship W3161666929A5091616184 @default.
- W3161666929 hasBestOaLocation W31616669291 @default.
- W3161666929 hasConcept C108583219 @default.
- W3161666929 hasConcept C132525143 @default.
- W3161666929 hasConcept C152745839 @default.
- W3161666929 hasConcept C154945302 @default.
- W3161666929 hasConcept C172707124 @default.
- W3161666929 hasConcept C41008148 @default.
- W3161666929 hasConcept C80444323 @default.
- W3161666929 hasConceptScore W3161666929C108583219 @default.
- W3161666929 hasConceptScore W3161666929C132525143 @default.
- W3161666929 hasConceptScore W3161666929C152745839 @default.
- W3161666929 hasConceptScore W3161666929C154945302 @default.
- W3161666929 hasConceptScore W3161666929C172707124 @default.
- W3161666929 hasConceptScore W3161666929C41008148 @default.
- W3161666929 hasConceptScore W3161666929C80444323 @default.
- W3161666929 hasLocation W31616669291 @default.
- W3161666929 hasLocation W31616669292 @default.
- W3161666929 hasLocation W31616669293 @default.
- W3161666929 hasLocation W31616669294 @default.
- W3161666929 hasLocation W31616669295 @default.
- W3161666929 hasOpenAccess W3161666929 @default.
- W3161666929 hasPrimaryLocation W31616669291 @default.
- W3161666929 hasRelatedWork W2126887587 @default.
- W3161666929 hasRelatedWork W2731899572 @default.
- W3161666929 hasRelatedWork W2939353110 @default.
- W3161666929 hasRelatedWork W3009238340 @default.
- W3161666929 hasRelatedWork W3215138031 @default.
- W3161666929 hasRelatedWork W4230611425 @default.
- W3161666929 hasRelatedWork W4312962853 @default.
- W3161666929 hasRelatedWork W4321369474 @default.
- W3161666929 hasRelatedWork W4327774331 @default.
- W3161666929 hasRelatedWork W4360585206 @default.
- W3161666929 isParatext "false" @default.
- W3161666929 isRetracted "false" @default.
- W3161666929 magId "3161666929" @default.
- W3161666929 workType "article" @default.