Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140205966> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3140205966 endingPage "222" @default.
- W3140205966 startingPage "203" @default.
- W3140205966 abstract "Abstract Deep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues. Formal verification is a promising avenue for tackling this difficulty, by formally certifying that networks are correct. We propose an SMT-based technique for verifying binarized neural networks — a popular kind of neural network, where some weights have been binarized in order to render the neural network more memory and energy efficient, and quicker to evaluate. One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components. Neural network verification is computationally very difficult, and so we propose here various optimizations, integrated into our SMT procedure as deduction steps, as well as an approach for parallelizing verification queries. We implement our technique as an extension to the Marabou framework, and use it to evaluate the approach on popular binarized neural network architectures." @default.
- W3140205966 created "2021-04-13" @default.
- W3140205966 creator A5026961968 @default.
- W3140205966 creator A5044509944 @default.
- W3140205966 creator A5050049437 @default.
- W3140205966 creator A5071719123 @default.
- W3140205966 date "2021-01-01" @default.
- W3140205966 modified "2023-10-14" @default.
- W3140205966 title "An SMT-Based Approach for Verifying Binarized Neural Networks" @default.
- W3140205966 cites W1481397690 @default.
- W3140205966 cites W2127470768 @default.
- W3140205966 cites W2141125852 @default.
- W3140205966 cites W2265846598 @default.
- W3140205966 cites W2300242332 @default.
- W3140205966 cites W2543296129 @default.
- W3140205966 cites W2565186948 @default.
- W3140205966 cites W2594877703 @default.
- W3140205966 cites W2754537581 @default.
- W3140205966 cites W2794609696 @default.
- W3140205966 cites W2892430965 @default.
- W3140205966 cites W2946149952 @default.
- W3140205966 cites W2957311447 @default.
- W3140205966 cites W2963054787 @default.
- W3140205966 cites W2963273111 @default.
- W3140205966 cites W2963673089 @default.
- W3140205966 cites W2967595108 @default.
- W3140205966 cites W2999803881 @default.
- W3140205966 cites W3007736072 @default.
- W3140205966 cites W3046662910 @default.
- W3140205966 cites W3047908945 @default.
- W3140205966 cites W3094683669 @default.
- W3140205966 cites W3096553286 @default.
- W3140205966 cites W3102139284 @default.
- W3140205966 cites W3190946860 @default.
- W3140205966 cites W3207272170 @default.
- W3140205966 doi "https://doi.org/10.1007/978-3-030-72013-1_11" @default.
- W3140205966 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7984573" @default.
- W3140205966 hasPublicationYear "2021" @default.
- W3140205966 type Work @default.
- W3140205966 sameAs 3140205966 @default.
- W3140205966 citedByCount "18" @default.
- W3140205966 countsByYear W31402059662021 @default.
- W3140205966 countsByYear W31402059662022 @default.
- W3140205966 countsByYear W31402059662023 @default.
- W3140205966 crossrefType "book-chapter" @default.
- W3140205966 hasAuthorship W3140205966A5026961968 @default.
- W3140205966 hasAuthorship W3140205966A5044509944 @default.
- W3140205966 hasAuthorship W3140205966A5050049437 @default.
- W3140205966 hasAuthorship W3140205966A5071719123 @default.
- W3140205966 hasBestOaLocation W31402059661 @default.
- W3140205966 hasConcept C119857082 @default.
- W3140205966 hasConcept C138885662 @default.
- W3140205966 hasConcept C154945302 @default.
- W3140205966 hasConcept C27206212 @default.
- W3140205966 hasConcept C2778738651 @default.
- W3140205966 hasConcept C2984842247 @default.
- W3140205966 hasConcept C41008148 @default.
- W3140205966 hasConcept C50644808 @default.
- W3140205966 hasConceptScore W3140205966C119857082 @default.
- W3140205966 hasConceptScore W3140205966C138885662 @default.
- W3140205966 hasConceptScore W3140205966C154945302 @default.
- W3140205966 hasConceptScore W3140205966C27206212 @default.
- W3140205966 hasConceptScore W3140205966C2778738651 @default.
- W3140205966 hasConceptScore W3140205966C2984842247 @default.
- W3140205966 hasConceptScore W3140205966C41008148 @default.
- W3140205966 hasConceptScore W3140205966C50644808 @default.
- W3140205966 hasLocation W31402059661 @default.
- W3140205966 hasLocation W31402059662 @default.
- W3140205966 hasOpenAccess W3140205966 @default.
- W3140205966 hasPrimaryLocation W31402059661 @default.
- W3140205966 hasRelatedWork W2791691546 @default.
- W3140205966 hasRelatedWork W2950066684 @default.
- W3140205966 hasRelatedWork W3012234327 @default.
- W3140205966 hasRelatedWork W3203168320 @default.
- W3140205966 hasRelatedWork W4288853838 @default.
- W3140205966 hasRelatedWork W4298388782 @default.
- W3140205966 hasRelatedWork W4317565044 @default.
- W3140205966 hasRelatedWork W4322008322 @default.
- W3140205966 hasRelatedWork W4379255972 @default.
- W3140205966 hasRelatedWork W1629725936 @default.
- W3140205966 isParatext "false" @default.
- W3140205966 isRetracted "false" @default.
- W3140205966 magId "3140205966" @default.
- W3140205966 workType "book-chapter" @default.