Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093485016> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3093485016 abstract "We present two methods to reduce the complexity of Bayesian network (BN) classifiers. First, we introduce quantization-aware training using the straight-through gradient estimator to quantize the parameters of BNs to few bits. Second, we extend a recently proposed differentiable tree-augmented naive Bayes (TAN) structure learning approach by also considering the model size. Both methods are motivated by recent developments in the deep learning community, and they provide effective means to trade off between model size and prediction accuracy, which is demonstrated in extensive experiments. Furthermore, we contrast quantized BN classifiers with quantized deep neural networks (DNNs) for small-scale scenarios which have hardly been investigated in the literature. We show Pareto optimal models with respect to model size, number of operations, and test error and find that both model classes are viable options." @default.
- W3093485016 created "2020-10-29" @default.
- W3093485016 creator A5014251134 @default.
- W3093485016 creator A5015798259 @default.
- W3093485016 creator A5019416885 @default.
- W3093485016 creator A5073596132 @default.
- W3093485016 date "2020-10-22" @default.
- W3093485016 modified "2023-09-26" @default.
- W3093485016 title "On Resource-Efficient Bayesian Network Classifiers and Deep Neural Networks" @default.
- W3093485016 cites W1533861849 @default.
- W3093485016 cites W1554944419 @default.
- W3093485016 cites W1585743408 @default.
- W3093485016 cites W178485974 @default.
- W3093485016 cites W1817561967 @default.
- W3093485016 cites W1836465849 @default.
- W3093485016 cites W1959608418 @default.
- W3093485016 cites W2095235480 @default.
- W3093485016 cites W2112796928 @default.
- W3093485016 cites W2137587467 @default.
- W3093485016 cites W2158396040 @default.
- W3093485016 cites W2242818861 @default.
- W3093485016 cites W2267635276 @default.
- W3093485016 cites W2300242332 @default.
- W3093485016 cites W2469490737 @default.
- W3093485016 cites W2547875792 @default.
- W3093485016 cites W2548228487 @default.
- W3093485016 cites W2808040408 @default.
- W3093485016 cites W2810075754 @default.
- W3093485016 cites W2963139738 @default.
- W3093485016 cites W2964121744 @default.
- W3093485016 cites W2964259004 @default.
- W3093485016 cites W2999963857 @default.
- W3093485016 cites W3120740533 @default.
- W3093485016 cites W3155646134 @default.
- W3093485016 hasPublicationYear "2020" @default.
- W3093485016 type Work @default.
- W3093485016 sameAs 3093485016 @default.
- W3093485016 citedByCount "0" @default.
- W3093485016 crossrefType "posted-content" @default.
- W3093485016 hasAuthorship W3093485016A5014251134 @default.
- W3093485016 hasAuthorship W3093485016A5015798259 @default.
- W3093485016 hasAuthorship W3093485016A5019416885 @default.
- W3093485016 hasAuthorship W3093485016A5073596132 @default.
- W3093485016 hasConcept C105795698 @default.
- W3093485016 hasConcept C107673813 @default.
- W3093485016 hasConcept C108583219 @default.
- W3093485016 hasConcept C119857082 @default.
- W3093485016 hasConcept C154945302 @default.
- W3093485016 hasConcept C185429906 @default.
- W3093485016 hasConcept C2984842247 @default.
- W3093485016 hasConcept C33724603 @default.
- W3093485016 hasConcept C33923547 @default.
- W3093485016 hasConcept C41008148 @default.
- W3093485016 hasConcept C50644808 @default.
- W3093485016 hasConceptScore W3093485016C105795698 @default.
- W3093485016 hasConceptScore W3093485016C107673813 @default.
- W3093485016 hasConceptScore W3093485016C108583219 @default.
- W3093485016 hasConceptScore W3093485016C119857082 @default.
- W3093485016 hasConceptScore W3093485016C154945302 @default.
- W3093485016 hasConceptScore W3093485016C185429906 @default.
- W3093485016 hasConceptScore W3093485016C2984842247 @default.
- W3093485016 hasConceptScore W3093485016C33724603 @default.
- W3093485016 hasConceptScore W3093485016C33923547 @default.
- W3093485016 hasConceptScore W3093485016C41008148 @default.
- W3093485016 hasConceptScore W3093485016C50644808 @default.
- W3093485016 hasLocation W30934850161 @default.
- W3093485016 hasOpenAccess W3093485016 @default.
- W3093485016 hasPrimaryLocation W30934850161 @default.
- W3093485016 hasRelatedWork W1553145417 @default.
- W3093485016 hasRelatedWork W168332103 @default.
- W3093485016 hasRelatedWork W2111533640 @default.
- W3093485016 hasRelatedWork W2326372119 @default.
- W3093485016 hasRelatedWork W2437421599 @default.
- W3093485016 hasRelatedWork W2522104961 @default.
- W3093485016 hasRelatedWork W2781494504 @default.
- W3093485016 hasRelatedWork W2785334672 @default.
- W3093485016 hasRelatedWork W2895998586 @default.
- W3093485016 hasRelatedWork W2963716487 @default.
- W3093485016 hasRelatedWork W2963859455 @default.
- W3093485016 hasRelatedWork W2995912923 @default.
- W3093485016 hasRelatedWork W3014908702 @default.
- W3093485016 hasRelatedWork W3037722013 @default.
- W3093485016 hasRelatedWork W3083548991 @default.
- W3093485016 hasRelatedWork W3114671438 @default.
- W3093485016 hasRelatedWork W3155646134 @default.
- W3093485016 hasRelatedWork W3194784700 @default.
- W3093485016 hasRelatedWork W3200990228 @default.
- W3093485016 hasRelatedWork W601603264 @default.
- W3093485016 isParatext "false" @default.
- W3093485016 isRetracted "false" @default.
- W3093485016 magId "3093485016" @default.
- W3093485016 workType "article" @default.