Continuous Bernoulli distribution (original) (raw)
In probability theory, statistics, and machine learning, the continuous Bernoulli distribution is a family of continuous probability distributions parameterized by a single shape parameter , defined on the unit interval , by: The continuous Bernoulli also defines an exponential family of distributions. Writing for the natural parameter, the density can be rewritten in canonical form:.
| Property | Value |
|---|---|
| dbo:abstract | In probability theory, statistics, and machine learning, the continuous Bernoulli distribution is a family of continuous probability distributions parameterized by a single shape parameter , defined on the unit interval , by: The continuous Bernoulli distribution arises in deep learning and computer vision, specifically in the context of variational autoencoders, for modeling the pixel intensities of natural images. As such, it defines a proper probabilistic counterpart for the commonly used binary cross entropy loss, which is often applied to continuous, -valued data. This practice amounts to ignoring the normalizing constant of the continuous Bernoulli distribution, since the binary cross entropy loss only defines a true log-likelihood for discrete, -valued data. The continuous Bernoulli also defines an exponential family of distributions. Writing for the natural parameter, the density can be rewritten in canonical form:. (en) |
| dbo:thumbnail | wiki-commons:Special:FilePath/CB_pdf.png?width=300 |
| dbo:wikiPageID | 64250099 (xsd:integer) |
| dbo:wikiPageLength | 6450 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1123006848 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Probability_distribution dbr:Bernoulli_distribution dbr:Beta_distribution dbr:Deep_learning dbr:Cross_entropy dbr:Machine_learning dbr:Simplex dbr:Statistics dbr:Computer_vision dbr:Identifiability dbr:Exponential_distribution dbr:Exponential_family dbr:Probability_density_function dbr:Probability_theory dbc:Exponential_family_distributions dbc:Continuous_distributions dbr:Probability_mass_function dbr:Shape_parameter dbr:Variational_autoencoder dbr:Natural_parameter dbr:Continuous-categorical dbr:File:CB_pdf.png |
| dbp:name | Continuous Bernoulli distribution (en) |
| dbp:pdf | where (en) |
| dbp:pdfImage | 325 (xsd:integer) |
| dbp:type | density (en) |
| dbp:wikiPageUsesTemplate | dbt:Distinguish dbt:Reflist dbt:Short_description dbt:Which dbt:Probability_distribution dbt:Probability_distributions |
| dct:subject | dbc:Exponential_family_distributions dbc:Continuous_distributions |
| rdf:type | owl:Thing |
| rdfs:comment | In probability theory, statistics, and machine learning, the continuous Bernoulli distribution is a family of continuous probability distributions parameterized by a single shape parameter , defined on the unit interval , by: The continuous Bernoulli also defines an exponential family of distributions. Writing for the natural parameter, the density can be rewritten in canonical form:. (en) |
| rdfs:label | Continuous Bernoulli distribution (en) |
| owl:differentFrom | dbr:Bernoulli_distribution |
| owl:sameAs | wikidata:Continuous Bernoulli distribution dbpedia-fa:Continuous Bernoulli distribution https://global.dbpedia.org/id/DZvgc |
| prov:wasDerivedFrom | wikipedia-en:Continuous_Bernoulli_distribution?oldid=1123006848&ns=0 |
| foaf:depiction | wiki-commons:Special:FilePath/CB_pdf.png |
| foaf:isPrimaryTopicOf | wikipedia-en:Continuous_Bernoulli_distribution |
| is dbo:wikiPageWikiLink of | dbr:List_of_probability_distributions dbr:Exponential_family dbr:List_of_things_named_after_members_of_the_Bernoulli_family |
| is foaf:primaryTopic of | wikipedia-en:Continuous_Bernoulli_distribution |
