Matches in SemOpenAlex for { <https://semopenalex.org/work/W3097661056> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3097661056 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.
- W3097661056 created "2020-11-09" @default.
- W3097661056 creator A5026961968 @default.
- W3097661056 creator A5044509944 @default.
- W3097661056 creator A5050049437 @default.
- W3097661056 creator A5071719123 @default.
- W3097661056 date "2021-03-19" @default.
- W3097661056 modified "2023-10-15" @default.
- W3097661056 title "An SMT-Based Approach for Verifying Binarized Neural Networks" @default.
- W3097661056 cites W1481397690 @default.
- W3097661056 cites W2127470768 @default.
- W3097661056 cites W2141125852 @default.
- W3097661056 cites W2163605009 @default.
- W3097661056 cites W2265846598 @default.
- W3097661056 cites W2267635276 @default.
- W3097661056 cites W2286365479 @default.
- W3097661056 cites W2300242332 @default.
- W3097661056 cites W2524428287 @default.
- W3097661056 cites W2543296129 @default.
- W3097661056 cites W2565186948 @default.
- W3097661056 cites W2594877703 @default.
- W3097661056 cites W2754537581 @default.
- W3097661056 cites W2794609696 @default.
- W3097661056 cites W2801079363 @default.
- W3097661056 cites W2807040120 @default.
- W3097661056 cites W2892430965 @default.
- W3097661056 cites W2957311447 @default.
- W3097661056 cites W2962835968 @default.
- W3097661056 cites W2963054787 @default.
- W3097661056 cites W2963735478 @default.
- W3097661056 cites W2963784236 @default.
- W3097661056 cites W2964299589 @default.
- W3097661056 cites W2967595108 @default.
- W3097661056 cites W2996098493 @default.
- W3097661056 cites W2999093589 @default.
- W3097661056 cites W2999803881 @default.
- W3097661056 cites W3007736072 @default.
- W3097661056 cites W3029066813 @default.
- W3097661056 cites W3046662910 @default.
- W3097661056 cites W3047908945 @default.
- W3097661056 cites W3094683669 @default.
- W3097661056 cites W3096553286 @default.
- W3097661056 cites W3102139284 @default.
- W3097661056 cites W3122363971 @default.
- W3097661056 doi "https://doi.org/10.26226/morressier.604907f41a80aac83ca25cda" @default.
- W3097661056 hasPublicationYear "2021" @default.
- W3097661056 type Work @default.
- W3097661056 sameAs 3097661056 @default.
- W3097661056 citedByCount "5" @default.
- W3097661056 countsByYear W30976610562021 @default.
- W3097661056 countsByYear W30976610562022 @default.
- W3097661056 countsByYear W30976610562023 @default.
- W3097661056 crossrefType "posted-content" @default.
- W3097661056 hasAuthorship W3097661056A5026961968 @default.
- W3097661056 hasAuthorship W3097661056A5044509944 @default.
- W3097661056 hasAuthorship W3097661056A5050049437 @default.
- W3097661056 hasAuthorship W3097661056A5071719123 @default.
- W3097661056 hasBestOaLocation W30976610562 @default.
- W3097661056 hasConcept C154945302 @default.
- W3097661056 hasConcept C41008148 @default.
- W3097661056 hasConcept C50644808 @default.
- W3097661056 hasConceptScore W3097661056C154945302 @default.
- W3097661056 hasConceptScore W3097661056C41008148 @default.
- W3097661056 hasConceptScore W3097661056C50644808 @default.
- W3097661056 hasLocation W30976610561 @default.
- W3097661056 hasLocation W30976610562 @default.
- W3097661056 hasOpenAccess W3097661056 @default.
- W3097661056 hasPrimaryLocation W30976610561 @default.
- W3097661056 hasRelatedWork W2159443810 @default.
- W3097661056 hasRelatedWork W2386387936 @default.
- W3097661056 hasRelatedWork W2390279801 @default.
- W3097661056 hasRelatedWork W2748952813 @default.
- W3097661056 hasRelatedWork W2899084033 @default.
- W3097661056 hasRelatedWork W3001020386 @default.
- W3097661056 hasRelatedWork W3107474891 @default.
- W3097661056 hasRelatedWork W4362499384 @default.
- W3097661056 hasRelatedWork W644753246 @default.
- W3097661056 hasRelatedWork W1629725936 @default.
- W3097661056 isParatext "false" @default.
- W3097661056 isRetracted "false" @default.
- W3097661056 magId "3097661056" @default.
- W3097661056 workType "article" @default.