Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310233487> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4310233487 abstract "Conditional density estimation (CDE) is the task of estimating the probability of an event conditioned on some inputs. A neural network (NN) can also be used to compute the output distribution for continuous-domain, which can be viewed as an extension of regression task. Nevertheless, it is difficult to explicitly approximate a distribution without knowing the information of its general form a priori. In order to fit an arbitrary conditional distribution, discretizing the continuous domain into bins is an effective strategy, as long as we have sufficiently narrow bins and very large data. However, collecting enough data is often hard to reach and falls far short of that ideal in many circumstances, especially in multivariate CDE for the curse of dimensionality. In this paper, we demonstrate the benefits of modeling free-form conditional distributions using a deconvolution-based neural net framework, coping with data deficiency problems in discretization. It has the advantage of being flexible but also takes advantage of the hierarchical smoothness offered by the deconvolution layers. We compare our method to a number of other density-estimation approaches and show that our Deconvolutional Density Network (DDN) outperforms the competing methods on many univariate and multivariate tasks. The code of DDN is available at https://github.com/NBICLAB/DDN." @default.
- W4310233487 created "2022-11-30" @default.
- W4310233487 creator A5023200059 @default.
- W4310233487 creator A5041859803 @default.
- W4310233487 creator A5053275663 @default.
- W4310233487 creator A5077604881 @default.
- W4310233487 date "2021-05-29" @default.
- W4310233487 modified "2023-09-30" @default.
- W4310233487 title "Deconvolutional Density Network: Modeling Free-Form Conditional Distributions" @default.
- W4310233487 doi "https://doi.org/10.48550/arxiv.2105.14367" @default.
- W4310233487 hasPublicationYear "2021" @default.
- W4310233487 type Work @default.
- W4310233487 citedByCount "0" @default.
- W4310233487 crossrefType "posted-content" @default.
- W4310233487 hasAuthorship W4310233487A5023200059 @default.
- W4310233487 hasAuthorship W4310233487A5041859803 @default.
- W4310233487 hasAuthorship W4310233487A5053275663 @default.
- W4310233487 hasAuthorship W4310233487A5077604881 @default.
- W4310233487 hasBestOaLocation W43102334871 @default.
- W4310233487 hasConcept C105795698 @default.
- W4310233487 hasConcept C111030470 @default.
- W4310233487 hasConcept C111472728 @default.
- W4310233487 hasConcept C11413529 @default.
- W4310233487 hasConcept C119857082 @default.
- W4310233487 hasConcept C126255220 @default.
- W4310233487 hasConcept C134306372 @default.
- W4310233487 hasConcept C138885662 @default.
- W4310233487 hasConcept C154945302 @default.
- W4310233487 hasConcept C161584116 @default.
- W4310233487 hasConcept C174576160 @default.
- W4310233487 hasConcept C185429906 @default.
- W4310233487 hasConcept C189508267 @default.
- W4310233487 hasConcept C33923547 @default.
- W4310233487 hasConcept C41008148 @default.
- W4310233487 hasConcept C43555835 @default.
- W4310233487 hasConcept C50644808 @default.
- W4310233487 hasConcept C73000952 @default.
- W4310233487 hasConcept C75553542 @default.
- W4310233487 hasConceptScore W4310233487C105795698 @default.
- W4310233487 hasConceptScore W4310233487C111030470 @default.
- W4310233487 hasConceptScore W4310233487C111472728 @default.
- W4310233487 hasConceptScore W4310233487C11413529 @default.
- W4310233487 hasConceptScore W4310233487C119857082 @default.
- W4310233487 hasConceptScore W4310233487C126255220 @default.
- W4310233487 hasConceptScore W4310233487C134306372 @default.
- W4310233487 hasConceptScore W4310233487C138885662 @default.
- W4310233487 hasConceptScore W4310233487C154945302 @default.
- W4310233487 hasConceptScore W4310233487C161584116 @default.
- W4310233487 hasConceptScore W4310233487C174576160 @default.
- W4310233487 hasConceptScore W4310233487C185429906 @default.
- W4310233487 hasConceptScore W4310233487C189508267 @default.
- W4310233487 hasConceptScore W4310233487C33923547 @default.
- W4310233487 hasConceptScore W4310233487C41008148 @default.
- W4310233487 hasConceptScore W4310233487C43555835 @default.
- W4310233487 hasConceptScore W4310233487C50644808 @default.
- W4310233487 hasConceptScore W4310233487C73000952 @default.
- W4310233487 hasConceptScore W4310233487C75553542 @default.
- W4310233487 hasLocation W43102334871 @default.
- W4310233487 hasOpenAccess W4310233487 @default.
- W4310233487 hasPrimaryLocation W43102334871 @default.
- W4310233487 hasRelatedWork W1599767198 @default.
- W4310233487 hasRelatedWork W1973623210 @default.
- W4310233487 hasRelatedWork W2183181906 @default.
- W4310233487 hasRelatedWork W2548777553 @default.
- W4310233487 hasRelatedWork W2961085424 @default.
- W4310233487 hasRelatedWork W3003265541 @default.
- W4310233487 hasRelatedWork W3169456383 @default.
- W4310233487 hasRelatedWork W4287871663 @default.
- W4310233487 hasRelatedWork W4306674287 @default.
- W4310233487 hasRelatedWork W4224009465 @default.
- W4310233487 isParatext "false" @default.
- W4310233487 isRetracted "false" @default.
- W4310233487 workType "article" @default.