Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895877180> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2895877180 abstract "We propose the BinaryGAN, a novel generative adversarial network (GAN) that uses binary neurons at the output layer of the generator. We employ the sigmoid-adjusted straight-through estimators to estimate the gradients for the binary neurons and train the whole network by end-to-end backpropogation. The proposed model is able to directly generate binary-valued predictions at test time. We implement such a model to generate binarized MNIST digits and experimentally compare the performance for different types of binary neurons, GAN objectives and network architectures. Although the results are still preliminary, we show that it is possible to train a GAN that has binary neurons and that the use of gradient estimators can be a promising direction for modeling discrete distributions with GANs. For reproducibility, the source code is available at this https URL ." @default.
- W2895877180 created "2018-10-26" @default.
- W2895877180 creator A5028026494 @default.
- W2895877180 creator A5061291906 @default.
- W2895877180 date "2018-10-10" @default.
- W2895877180 modified "2023-09-27" @default.
- W2895877180 title "Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation." @default.
- W2895877180 cites W2099471712 @default.
- W2895877180 cites W2242818861 @default.
- W2895877180 cites W2592298275 @default.
- W2895877180 cites W2798861951 @default.
- W2895877180 cites W2962879692 @default.
- W2895877180 cites W2963681776 @default.
- W2895877180 hasPublicationYear "2018" @default.
- W2895877180 type Work @default.
- W2895877180 sameAs 2895877180 @default.
- W2895877180 citedByCount "2" @default.
- W2895877180 countsByYear W28958771802019 @default.
- W2895877180 countsByYear W28958771802020 @default.
- W2895877180 crossrefType "posted-content" @default.
- W2895877180 hasAuthorship W2895877180A5028026494 @default.
- W2895877180 hasAuthorship W2895877180A5061291906 @default.
- W2895877180 hasConcept C105795698 @default.
- W2895877180 hasConcept C11413529 @default.
- W2895877180 hasConcept C121332964 @default.
- W2895877180 hasConcept C153180895 @default.
- W2895877180 hasConcept C154945302 @default.
- W2895877180 hasConcept C155032097 @default.
- W2895877180 hasConcept C163258240 @default.
- W2895877180 hasConcept C177264268 @default.
- W2895877180 hasConcept C185429906 @default.
- W2895877180 hasConcept C190502265 @default.
- W2895877180 hasConcept C199360897 @default.
- W2895877180 hasConcept C2776760102 @default.
- W2895877180 hasConcept C2780992000 @default.
- W2895877180 hasConcept C33923547 @default.
- W2895877180 hasConcept C41008148 @default.
- W2895877180 hasConcept C48372109 @default.
- W2895877180 hasConcept C50644808 @default.
- W2895877180 hasConcept C62520636 @default.
- W2895877180 hasConcept C74296488 @default.
- W2895877180 hasConcept C81388566 @default.
- W2895877180 hasConcept C94375191 @default.
- W2895877180 hasConceptScore W2895877180C105795698 @default.
- W2895877180 hasConceptScore W2895877180C11413529 @default.
- W2895877180 hasConceptScore W2895877180C121332964 @default.
- W2895877180 hasConceptScore W2895877180C153180895 @default.
- W2895877180 hasConceptScore W2895877180C154945302 @default.
- W2895877180 hasConceptScore W2895877180C155032097 @default.
- W2895877180 hasConceptScore W2895877180C163258240 @default.
- W2895877180 hasConceptScore W2895877180C177264268 @default.
- W2895877180 hasConceptScore W2895877180C185429906 @default.
- W2895877180 hasConceptScore W2895877180C190502265 @default.
- W2895877180 hasConceptScore W2895877180C199360897 @default.
- W2895877180 hasConceptScore W2895877180C2776760102 @default.
- W2895877180 hasConceptScore W2895877180C2780992000 @default.
- W2895877180 hasConceptScore W2895877180C33923547 @default.
- W2895877180 hasConceptScore W2895877180C41008148 @default.
- W2895877180 hasConceptScore W2895877180C48372109 @default.
- W2895877180 hasConceptScore W2895877180C50644808 @default.
- W2895877180 hasConceptScore W2895877180C62520636 @default.
- W2895877180 hasConceptScore W2895877180C74296488 @default.
- W2895877180 hasConceptScore W2895877180C81388566 @default.
- W2895877180 hasConceptScore W2895877180C94375191 @default.
- W2895877180 hasLocation W28958771801 @default.
- W2895877180 hasOpenAccess W2895877180 @default.
- W2895877180 hasPrimaryLocation W28958771801 @default.
- W2895877180 hasRelatedWork W124100583 @default.
- W2895877180 hasRelatedWork W1489744657 @default.
- W2895877180 hasRelatedWork W1510333322 @default.
- W2895877180 hasRelatedWork W155909208 @default.
- W2895877180 hasRelatedWork W2005971284 @default.
- W2895877180 hasRelatedWork W2021384351 @default.
- W2895877180 hasRelatedWork W2095584476 @default.
- W2895877180 hasRelatedWork W2104243559 @default.
- W2895877180 hasRelatedWork W2145915830 @default.
- W2895877180 hasRelatedWork W2195511199 @default.
- W2895877180 hasRelatedWork W2389539679 @default.
- W2895877180 hasRelatedWork W2798861951 @default.
- W2895877180 hasRelatedWork W2964111160 @default.
- W2895877180 hasRelatedWork W2978447704 @default.
- W2895877180 hasRelatedWork W2990498047 @default.
- W2895877180 hasRelatedWork W3005559199 @default.
- W2895877180 hasRelatedWork W3023625105 @default.
- W2895877180 hasRelatedWork W3200692463 @default.
- W2895877180 hasRelatedWork W3213073654 @default.
- W2895877180 hasRelatedWork W2185467021 @default.
- W2895877180 isParatext "false" @default.
- W2895877180 isRetracted "false" @default.
- W2895877180 magId "2895877180" @default.
- W2895877180 workType "article" @default.