Mixture model (original) (raw)
Der Begriff Mischverteilung oder zusammengesetzte Verteilung stammt aus der Wahrscheinlichkeitsrechnung. Es handelt sich dabei um eine Wahrscheinlichkeitsverteilung, die ein gewichtetes Mittel von mehreren Wahrscheinlichkeitsverteilungen ist. Das heißt zum Beispiel seien die Wahrscheinlichkeitsdichten von verschiedenen Verteilungen, dann ist die Dichte der Mischverteilung von der Form wobei normalisierte Gewichte sind. Dadurch entsteht eine Mischung von Zufallsgrößen aus mehreren verschiedenen Grundgesamtheiten.
| Property | Value |
|---|---|
| dbo:abstract | في الإحصائيات، يعد نموذج الخليط نموذجًا احتماليًا لتمثيل وجود مجموعات سكانية فرعية ضمن إجمالي عدد السكان، دون تحديد أي من مجموعة البيانات التي تمت ملاحظتها هي المجموعة الفرعية التي تنتمي إليها الملاحظات الفردية. يتطابق نموذج الخليط كلياً مع توزيع الخليط الذي يمثل التوزيع الاحتمالي للتدقيقات في إجمالي السكان. ولذلك، في حين أن المشكلات المتعلقة بـ «توزيعات المزيج» ترتبط باشتقاق مميزات إجمالي السكان من تلك الخاصة بالسكان الفرعيين، فإن «نماذج المزيج» يعد مناسباً لإجراء استنتاجات إحصائية حول خصائص المجموعات الفرعية مع الأخذ بعين الاعتبار من الملاحظات فقط على تجمع السكان، دون معلومات هوية السكان الفرعية. تتضمن بعض طرق تنفيذ نماذج المزيج بعض خطوات التي تُنسب إلى هويات السكان الفرعية المفترضة إلى الملاحظات الفردية (أو الأوزان تجاه هذه الفئات الفرعية)، وفي هذه الحالة يجب اعتبارها أنواعًا من أنواع التعلم الغير خاضع للرقابة أو إجراءات التجميع. ولذاك، لا تنطوي جميع إجراءات الاستدلال على مثل هذه الخطوات. لا يجب الخط بين النوذج اخليطي والبيانات التركيبية، أي تلك البيانات التي تكون مقيدة (1، 100٪، إلخ.). لذلك، يمكن اعتبارهم جميعا نماذج مختلطة، حيث يتم أخذ عينات من السكان بشكل عشوائي. على العكس من ذلك، يمكن اعتبار نماذج الخليط كنماذج تركيبية، حيث تم تطبيع إجمالي حجم القراءة إلى 1. (ar) Der Begriff Mischverteilung oder zusammengesetzte Verteilung stammt aus der Wahrscheinlichkeitsrechnung. Es handelt sich dabei um eine Wahrscheinlichkeitsverteilung, die ein gewichtetes Mittel von mehreren Wahrscheinlichkeitsverteilungen ist. Das heißt zum Beispiel seien die Wahrscheinlichkeitsdichten von verschiedenen Verteilungen, dann ist die Dichte der Mischverteilung von der Form wobei normalisierte Gewichte sind. Dadurch entsteht eine Mischung von Zufallsgrößen aus mehreren verschiedenen Grundgesamtheiten. (de) En probabilité et en statistiques, une loi de mélange est la loi de probabilité d'une variable aléatoire s'obtenant à partir d'une famille de variables aléatoires de la manière suivante : une variable aléatoire est choisie au hasard parmi la famille de variables aléatoires donnée, puis la valeur de la variable aléatoire sélectionnée est réalisée. Les variables aléatoires sous-jacentes peuvent être des nombres réels aléatoires, ou des vecteurs aléatoires (chacun ayant la même dimension), auquel cas la répartition du mélange est une répartition à plusieurs variables. Dans les cas où chacune des variables aléatoires sous-jacente est continue, la variable finale sera également continue et sa fonction de densité de probabilité est parfois appelée densité de mélange. La fonction de répartition (et la densité de probabilité si elle existe) peut être exprimée sous forme d'une combinaison convexe (par exemple une somme pondérée, avec des probabilités positives dont la somme est 1) d'autres fonctions de loi et de fonctions de densité. Les répartitions individuelles qui sont combinées pour former la loi du mélange sont appelées les composants du mélange, et les probabilités associées à chaque composant sont appelées les probabilités du mélange. Le nombre de composants dans la loi de mélange est souvent limitée, bien que dans certains cas, les composants peuvent être indénombrables. Une distinction doit être faite entre une variable aléatoire dont la loi est une somme pondérée de composants, et une variable qui s'écrit comme la somme de variables aléatoires, auquel cas sa loi est donnée par le produit de convolution des lois des variables sommées. À titre d'exemple, la somme de deux variables aléatoires conjointement normalement distribuées, chacun avec des moyennes différentes, aura toujours une loi normale. D'un autre côté, une densité de mélange conçue comme un mélange de deux lois normales, avec des moyennes différentes, aura deux pics à condition que les deux moyennes soient assez éloignées, ce qui montre que cette loi est radicalement différente d'une loi normale. La loi de mélange existe dans de nombreux contextes dans la littérature et se pose naturellement là où une contient deux ou plusieurs . Elles sont également parfois utilisées comme moyen de représentation des lois non normales. L'analyse des données concernant les modèles statistiques portant sur les lois de mélange est appelée modèle de mélange. (fr) In statistics, a mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the sub-population to which an individual observation belongs. Formally a mixture model corresponds to the mixture distribution that represents the probability distribution of observations in the overall population. However, while problems associated with "mixture distributions" relate to deriving the properties of the overall population from those of the sub-populations, "mixture models" are used to make statistical inferences about the properties of the sub-populations given only observations on the pooled population, without sub-population identity information. Mixture models should not be confused with models for compositional data, i.e., data whose components are constrained to sum to a constant value (1, 100%, etc.). However, compositional models can be thought of as mixture models, where members of the population are sampled at random. Conversely, mixture models can be thought of as compositional models, where the total size reading population has been normalized to 1. (en) En statistiques, un modèle de mélange est un modèle statistique permettant de modéliser différentes sous-populations dans la population globale sans que ces sous-populations soient identifiées dans les données par une variable observée. (fr) 혼합 모델(Mixture model)은 통계학에서 전체 집단안의 하위 집단의 존재를 나타내기 위한 확률 모델이다. 좀 더 형식적으로는 전체 집단의 확률 분포를 나타내는 (Mixture distribution)에 해당한다. 그러나 "혼합 분포"와 관련된 문제들은 하위 집단들로부터 전체 집단의 특징들을 얻는 것에 관련된 반면, "혼합 모델"들은 관찰된 집단이 주어졌을 때 하위 집단들의 특징들에 대해 통계적 추론을 하기 위해 쓰인다. 혼합 모델의 좀더 구체적인 사용 용도로는, 만약 관찰된 변수와 잠재 변수의 결합 분포를 정의한다면, 관찰된 변수들의 분포는 모든 잠재 변수에 대해 주변화(marginalize)함으로써 구할 수 있다. 이렇게 함으로써 관찰된 변수의 복잡한 분포를 잠재변수를 사용하여 더 단순하게 표현할 수 있다. 혼합 모델은 이러한 잠재변수를 가정하여 복잡한 분포를 추정하는데 사용된다. 또, 혼합 모델은 데이터를 군집화(clustering)하는 데 쓰일 수 있다. 잠재 변수를 포함하는 모델의 최대 우도 추정(Maximum likelihood estimation)을 위해서는 기대값 최대화(expectation-maximization) 알고리즘이 사용된다.가우스 혼합 모델은 데이터마이닝, 패턴 인식, 머신 러닝, 통계분석 등에 광범위하게 쓰인다. 이 때 모델의 파라미터들은 EM 알고리즘을 통해 구한다. (ko) Una mistura di distribuzioni è una variabile casuale, la cui funzione di probabilità (nel caso di una variabile casuale discreta) o la cui funzione di densità di probabilità (nel caso di una variabile casuale continua) è data da una media ponderata di funzioni di probabilità o densità di altre variabili casuali. Nel caso di una mistura finita di distribuzioni continue la funzione di densità di probabilità è descritta in generale da con il vincolo che e dove sono k funzioni di probabilità, le quali possono a loro volta avere dei parametri che le caratterizzano. Ad esempio una mistura di due distribuzioni normali ha come funzione di densità di probabilità dove e è la funzione di densità di probabilità di una variabile casuale normale. Un teorema di rappresentazione di Lebesgue assicura che ogni variabile casuale è rappresentabile come mistura di distribuzioni del tipo continuo e/o discreto e/o singolare. Uno dei casi nei quali si ricorre ad una mistura di distribuzioni è quello delle subpopolazioni, ovvero quando una popolazione (di valori) è composta da più sottopopolazioni ciascuna con una propria distribuzione dei valori. Ad esempio, se si ritiene che sia l'altezza degli uomini che l'altezza delle donne sia distribuita come una normale, ma con la media per gli uomini maggiore della media delle donne, allora l'altezza degli individui senza distinzione di sesso è una mistura di due distribuzioni normali. Nell'ambito dell'inferenza bayesiana si fa ampio ricorso a misture basate sulle coniugate prior come nel caso della Binomiale con la Beta (v.c. betabinomiale), la Poissoniana con la Gamma (v.c. Poisson-Gamma), l'esponenziale o la Gamma con la Gamma stessa. (it) Em estatística, um modelo mistura é um modelo probabilístico para representar a presença de sub-populações dentro de uma população geral, sem exigir que um conjunto de dados observados devam identificar as sub-populações que pertençam a uma observação individual. Formalmente um modelo mistura corresponde à que representa a de observações na população em geral. No entanto, enquanto os problemas associados com "distribuições mistura" relacionadas às derivações da população geral daquelas das sub-populações, "modelos mistura" são usados para realizar inferências estatísticas sobre as propriedades das sub-populações dadas apenas observações sobre a amostragem populacional, sem informações de identidade de sub-população. Algumas maneiras de implementar modelos de mistura envolvem etapas que atribuem determinados postulados de identidades de sub-população para observações individuais (ou pesos para essas sub-populações), caso em que estas podem ser consideradas como um tipo de ou procedimentos em . No entanto, nem todos os processos de inferência envolvem tais etapas. Modelos de mistura não deve ser confundidos com os modelos para dados composicionais, i.e., dados cujos componentes são constrangidos a soma a um valor constante (1, 100%, etc.). (pt) 在統計學中，混合模型（Mixture model）是用於表示母體中子母體的存在的機率模型，換句話說，混合模型表示了測量結果在母體中的機率分布，它是一個由數個子母體之機率分布組成的。混合模型不要求測量結果供關於各個子母體之機率分布的資訊即可計算測量結果在母體分布中的機率。 (zh) |
| dbo:thumbnail | wiki-commons:Special:FilePath/Nonbayesian-gaussian-mixture.svg?width=300 |
| dbo:wikiPageExternalLink | https://vincentfpgarcia.github.com/jMEF/ http://wiki.stat.ucla.edu/socr/index.php/SOCR_EduMaterials_Activities_2D_PointSegmentation_EM_Mixture http://stat.duke.edu/gpustatsci/software.html http://www.carolalexander.org/publish/download/JournalArticles/PDFs/JBF2004.pdf http://www.enterface.net/enterface05/docs/results/reports/project5.pdf https://scikits.appspot.com/ http://dro.dur.ac.uk/16022/1/16022.pdf https://cran.r-project.org/web/packages/mclust/index.html http://numerical.recipes/book https://www.cs.ru.nl/~ali/index_files/EM.m http://www.ceremade.dauphine.fr/%7Exian/mixo.pdf http://www.csse.monash.edu.au/~dld/Snob.html http://www.csse.monash.edu.au/~dld/mixturemodel.html http://scikit-learn.org/stable/modules/mixture.html https://mpatacchiola.github.io/blog/2020/07/31/gaussian-mixture-models.html http://www.pymix.org https://archive.org/details/finitemixturemod00geof https://github.com/juandavm/em4gmm https://github.com/thaines/helit/tree/master/dpgmm http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do%3FobjectId=18785&objectType=FILE |
| dbo:wikiPageID | 871681 (xsd:integer) |
| dbo:wikiPageLength | 58094 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1117202744 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Bayesian_inference dbc:Probabilistic_models dbr:Probability_distribution dbr:Psychology dbr:SciPy dbr:Electrophoresis dbr:Method_of_moments_(statistics) dbr:Mixture_(probability) dbr:Multinomial_distribution dbr:Copula_(statistics) dbr:SOCR dbr:Bayes'_theorem dbr:Bernoulli_distribution dbr:Botany dbc:Cluster_analysis dbr:Hyperparameter dbr:Variance dbr:International_Conference_on_Acoustics,_Speech,_and_Signal_Processing dbr:Volatility_smile dbr:Conditional_probability dbr:Maximum_Likelihood dbr:Mean dbr:Measure_(mathematics) dbr:Genetics dbr:Outlier dbr:Geology dbr:Mixture_distribution dbr:Mode_(statistics) dbr:Multivariate_normal_distribution dbr:Concentration_parameter dbr:Conjugate_prior dbr:Convex_hull dbr:Statistical_inference dbr:Arithmetic_mean dbr:Log-normal_distribution dbr:Statistics dbc:Latent_variable_models dbr:Compositional_data dbr:Zipf's_law dbr:Zoology dbr:Student's_t-distribution dbc:Machine_learning dbr:Walter_Frank_Raphael_Weldon dbr:Heavy-tailed_distribution dbr:K-means_clustering dbr:Latent_Dirichlet_allocation dbr:Linear_subspace dbr:Local_volatility dbr:Logarithmically_concave_function dbr:Agriculture dbr:Economics dbr:Exponential_distribution dbr:Normal_distribution dbr:Palaeontology dbr:Dirichlet_distribution dbr:Graphical_model dbr:Parametric_family dbr:Gaussian_distribution dbr:Hierarchical_Bayes_model dbr:Mathematical_proof dbr:Posterior_probability dbr:Karl_Pearson dbr:Latent_variable dbr:Bingham_distribution dbr:Binomial_distribution dbr:Hidden_Markov_model dbr:Pixel dbr:Point_set_registration dbr:Poisson_distribution dbr:Spectral_method dbr:Circular_error_probable dbr:Finance dbr:Expectation-maximization_algorithm dbr:Image_segmentation dbr:Minimum_Message_Length dbr:Minimum_message_length dbr:Negative_binomial_distribution dbr:Categorical_distribution dbr:RANSAC dbr:Real_coordinate_space dbr:Markov_chain dbr:Maximum_likelihood dbr:Medicine dbr:Predictive_maintenance dbr:Exponential_growth dbr:Subspace_Gaussian_mixture_model dbr:Fishery dbr:Gibbs_sampling dbr:Multivariate_t-distribution dbr:Overfitting dbr:Topic_model dbr:Christopher_M._Bishop dbr:Iterative_algorithm dbr:Subpopulation dbr:Singular_Value_Decomposition dbr:Financial_derivatives dbr:Gaussian_mixture_model dbr:Independent_identically_distributed dbr:Mixture_density dbr:Prior_distribution dbr:Probabilistic_model dbr:Expectation_maximization dbr:Expectation_value dbr:Jump-diffusion_model dbr:Kolmogorov–Smirnov dbr:Dynamical_consistency dbr:File:Bayesian-categorical-mixture.svg dbr:File:Bayesian-gaussian-mixture.svg dbr:File:Movie.gif dbr:File:Nonbayesian-categorical-mixture.svg dbr:File:Nonbayesian-gaussian-mixture.svg dbr:File:Normal_distribution_pdf.png dbr:Flexible_Mixture_Model_(FMM) dbr:International_Conference_on_Imaging_Systems_and_Techniques dbr:Plug-in_estimates dbr:Posterior_sampling dbr:File:Parameter_estimation_process_infinite_Gaussian_mixture_model.webm |
| dbp:wikiPageUsesTemplate | dbt:= dbt:Cite_book dbt:Cite_conference dbt:Cite_journal dbt:Clear dbt:Distinguish dbt:Full_citation_needed dbt:Reflist dbt:See_also dbt:Slink dbt:Vague |
| dct:subject | dbc:Probabilistic_models dbc:Cluster_analysis dbc:Latent_variable_models dbc:Machine_learning |
| gold:hypernym | dbr:Model |
| rdf:type | owl:Thing dbo:Person yago:WikicatLatentVariableModels yago:WikicatStatisticalModels yago:Assistant109815790 yago:CausalAgent100007347 yago:LivingThing100004258 yago:Model110324560 yago:Object100002684 yago:Organism100004475 yago:Person100007846 yago:PhysicalEntity100001930 yago:Worker109632518 yago:YagoLegalActor yago:YagoLegalActorGeo yago:Whole100003553 yago:WikicatProbabilisticModels |
| rdfs:comment | Der Begriff Mischverteilung oder zusammengesetzte Verteilung stammt aus der Wahrscheinlichkeitsrechnung. Es handelt sich dabei um eine Wahrscheinlichkeitsverteilung, die ein gewichtetes Mittel von mehreren Wahrscheinlichkeitsverteilungen ist. Das heißt zum Beispiel seien die Wahrscheinlichkeitsdichten von verschiedenen Verteilungen, dann ist die Dichte der Mischverteilung von der Form wobei normalisierte Gewichte sind. Dadurch entsteht eine Mischung von Zufallsgrößen aus mehreren verschiedenen Grundgesamtheiten. (de) En statistiques, un modèle de mélange est un modèle statistique permettant de modéliser différentes sous-populations dans la population globale sans que ces sous-populations soient identifiées dans les données par une variable observée. (fr) 在統計學中，混合模型（Mixture model）是用於表示母體中子母體的存在的機率模型，換句話說，混合模型表示了測量結果在母體中的機率分布，它是一個由數個子母體之機率分布組成的。混合模型不要求測量結果供關於各個子母體之機率分布的資訊即可計算測量結果在母體分布中的機率。 (zh) في الإحصائيات، يعد نموذج الخليط نموذجًا احتماليًا لتمثيل وجود مجموعات سكانية فرعية ضمن إجمالي عدد السكان، دون تحديد أي من مجموعة البيانات التي تمت ملاحظتها هي المجموعة الفرعية التي تنتمي إليها الملاحظات الفردية. يتطابق نموذج الخليط كلياً مع توزيع الخليط الذي يمثل التوزيع الاحتمالي للتدقيقات في إجمالي السكان. ولذلك، في حين أن المشكلات المتعلقة بـ «توزيعات المزيج» ترتبط باشتقاق مميزات إجمالي السكان من تلك الخاصة بالسكان الفرعيين، فإن «نماذج المزيج» يعد مناسباً لإجراء استنتاجات إحصائية حول خصائص المجموعات الفرعية مع الأخذ بعين الاعتبار من الملاحظات فقط على تجمع السكان، دون معلومات هوية السكان الفرعية. (ar) En probabilité et en statistiques, une loi de mélange est la loi de probabilité d'une variable aléatoire s'obtenant à partir d'une famille de variables aléatoires de la manière suivante : une variable aléatoire est choisie au hasard parmi la famille de variables aléatoires donnée, puis la valeur de la variable aléatoire sélectionnée est réalisée. Les variables aléatoires sous-jacentes peuvent être des nombres réels aléatoires, ou des vecteurs aléatoires (chacun ayant la même dimension), auquel cas la répartition du mélange est une répartition à plusieurs variables. (fr) In statistics, a mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the sub-population to which an individual observation belongs. Formally a mixture model corresponds to the mixture distribution that represents the probability distribution of observations in the overall population. However, while problems associated with "mixture distributions" relate to deriving the properties of the overall population from those of the sub-populations, "mixture models" are used to make statistical inferences about the properties of the sub-populations given only observations on the pooled population, without sub-population identity information. (en) Una mistura di distribuzioni è una variabile casuale, la cui funzione di probabilità (nel caso di una variabile casuale discreta) o la cui funzione di densità di probabilità (nel caso di una variabile casuale continua) è data da una media ponderata di funzioni di probabilità o densità di altre variabili casuali. Nel caso di una mistura finita di distribuzioni continue la funzione di densità di probabilità è descritta in generale da con il vincolo che e dove sono k funzioni di probabilità, le quali possono a loro volta avere dei parametri che le caratterizzano. (it) 혼합 모델(Mixture model)은 통계학에서 전체 집단안의 하위 집단의 존재를 나타내기 위한 확률 모델이다. 좀 더 형식적으로는 전체 집단의 확률 분포를 나타내는 (Mixture distribution)에 해당한다. 그러나 "혼합 분포"와 관련된 문제들은 하위 집단들로부터 전체 집단의 특징들을 얻는 것에 관련된 반면, "혼합 모델"들은 관찰된 집단이 주어졌을 때 하위 집단들의 특징들에 대해 통계적 추론을 하기 위해 쓰인다. 혼합 모델의 좀더 구체적인 사용 용도로는, 만약 관찰된 변수와 잠재 변수의 결합 분포를 정의한다면, 관찰된 변수들의 분포는 모든 잠재 변수에 대해 주변화(marginalize)함으로써 구할 수 있다. 이렇게 함으로써 관찰된 변수의 복잡한 분포를 잠재변수를 사용하여 더 단순하게 표현할 수 있다. 혼합 모델은 이러한 잠재변수를 가정하여 복잡한 분포를 추정하는데 사용된다. 또, 혼합 모델은 데이터를 군집화(clustering)하는 데 쓰일 수 있다. (ko) Em estatística, um modelo mistura é um modelo probabilístico para representar a presença de sub-populações dentro de uma população geral, sem exigir que um conjunto de dados observados devam identificar as sub-populações que pertençam a uma observação individual. Formalmente um modelo mistura corresponde à que representa a de observações na população em geral. No entanto, enquanto os problemas associados com "distribuições mistura" relacionadas às derivações da população geral daquelas das sub-populações, "modelos mistura" são usados para realizar inferências estatísticas sobre as propriedades das sub-populações dadas apenas observações sobre a amostragem populacional, sem informações de identidade de sub-população. (pt) |
| rdfs:label | نموذج الخليط (ar) Mischverteilung (de) Loi de mélange (fr) Modèle de mélange (fr) Mistura di distribuzioni (it) 혼합 모델 (ko) Mixture model (en) Modelo mistura (pt) 混合模型 (zh) |
| rdfs:seeAlso | dbr:Mixture_distribution |
| owl:differentFrom | dbr:Mixed_model |
| owl:sameAs | freebase:Mixture model yago-res:Mixture model wikidata:Mixture model wikidata:Mixture model dbpedia-ar:Mixture model dbpedia-de:Mixture model dbpedia-fr:Mixture model dbpedia-fr:Mixture model dbpedia-it:Mixture model dbpedia-ko:Mixture model dbpedia-pt:Mixture model http://ta.dbpedia.org/resource/கலப்பமைப்பு dbpedia-zh:Mixture model https://global.dbpedia.org/id/gNUF |
| prov:wasDerivedFrom | wikipedia-en:Mixture_model?oldid=1117202744&ns=0 |
| foaf:depiction | wiki-commons:Special:FilePath/Bayesian-categorical-mixture.svg wiki-commons:Special:FilePath/Bayesian-gaussian-mixture.svg wiki-commons:Special:FilePath/Movie.gif wiki-commons:Special:FilePath/Nonbayesian-categorical-mixture.svg wiki-commons:Special:FilePath/Nonbayesian-gaussian-mixture.svg wiki-commons:Special:FilePath/Normal_distribution_pdf.png |
| foaf:isPrimaryTopicOf | wikipedia-en:Mixture_model |
| is dbo:wikiPageRedirects of | dbr:Mixture_models dbr:Multivariate_Gaussian_mixture_model dbr:Infinite_mixture_model dbr:Finite_mixture_model dbr:Finite_mixture_models dbr:Categorical_mixture_model dbr:Gaussian_mixture_model dbr:Mixture_coefficient dbr:Mixture_modeling dbr:Mixture_of_Gaussians dbr:Mixture_of_gaussians dbr:Mixtures_of_Gaussian dbr:Mixtures_of_Gaussians dbr:Contaminated_Gaussian_noise dbr:Latent_profile_analysis |
| is dbo:wikiPageWikiLink of | dbr:Programming_with_Big_Data_in_R dbr:Entropy_estimation dbr:Mixture_(probability) dbr:Naive_Bayes_classifier dbr:Metalog_distribution dbr:New_Zealand_Attitudes_and_Values_Study dbr:One-shot_learning dbr:Bayesian_network dbr:Anoura dbr:Deep_learning dbr:Dependent_Dirichlet_process dbr:EM_algorithm_and_GMM_model dbr:GMM dbr:Comparison_of_electoral_systems dbr:Conceptual_clustering dbr:Ana_Justel dbr:Geoffrey_McLachlan dbr:Outlier dbr:Functional_data_analysis dbr:Generative_model dbr:Mixture_distribution dbr:Mixture_models dbr:Multivariate_Gaussian_mixture_model dbr:Multivariate_normal_distribution dbr:Damiano_Brigo dbr:Eprapah_Creek dbr:Structural_equation_modeling dbr:Cluster-weighted_modeling dbr:Compositional_data dbr:Emotion_recognition dbr:Kernel_embedding_of_distributions dbr:Pattern_recognition dbr:Product_of_experts dbr:Statistical_population dbr:MyDemocracy.ca dbr:Bruce_G._Lindsay dbr:CMU_Sphinx dbr:Adele_Cutler dbr:Dark_triad dbr:Jump_diffusion dbr:K-means_clustering dbr:Sexual_dimorphism_measures dbr:Daniel_J._Bauer dbr:Euclidean_minimum_spanning_tree dbr:Exponential_family dbr:Fabio_Mercurio dbr:Financial_economics dbr:Financial_risk_management dbr:Dirichlet-multinomial_distribution dbr:Dirichlet_distribution dbr:Fokker–Planck_equation dbr:Granular_computing dbr:List_of_things_named_after_Carl_Friedrich_Gauss dbr:Speech_recognition dbr:Attractor_network dbr:Hurdle_model dbr:Jiayang_Sun dbr:Kaye_Basford dbr:Sylvia_Frühwirth-Schnatter dbr:Heteroclinic_channels dbr:Automatic_target_recognition dbr:Market_segmentation dbr:Finance dbr:Michael_J._Black dbr:Minimum_message_length dbr:Categorical_distribution dbr:Maximum_a_posteriori_estimation dbr:Variational_Bayesian_methods dbr:Infinite_mixture_model dbr:Trajectory_inference dbr:Expectation–maximization_algorithm dbr:List_of_statistics_articles dbr:Robust_statistics dbr:Subspace_Gaussian_mixture_model dbr:Gibbs_sampling dbr:Non-uniform_random_variate_generation dbr:Time_delay_neural_network dbr:Speaker_diarisation dbr:Shifted_Gompertz_distribution dbr:Outline_of_machine_learning dbr:Random_sample_consensus dbr:Finite_mixture_model dbr:Finite_mixture_models dbr:Categorical_mixture_model dbr:Gaussian_mixture_model dbr:Mixture_coefficient dbr:Mixture_modeling dbr:Mixture_of_Gaussians dbr:Mixture_of_gaussians dbr:Mixtures_of_Gaussian dbr:Mixtures_of_Gaussians dbr:Contaminated_Gaussian_noise dbr:Latent_profile_analysis |
| is rdfs:seeAlso of | dbr:Mixture_distribution |
| is owl:differentFrom of | dbr:Mixed_model |
| is foaf:primaryTopic of | wikipedia-en:Mixture_model |
