Statements (53)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
statistical analysis
|
| gptkbp:application |
Speech recognition
Image segmentation Anomaly detection Background subtraction |
| gptkbp:assumes |
Data generated from a mixture of Gaussians
|
| gptkbp:canBe |
Bayesian inference
Dimensionality reduction Maximum likelihood estimation Multivariate Univariate Model selection Data generation Missing data imputation Soft clustering |
| gptkbp:canBeRegularizedBy |
Dirichlet prior
|
| gptkbp:category |
Probabilistic model
Unsupervised learning |
| gptkbp:componentDistribution |
gptkb:Gaussian_distribution
|
| gptkbp:extendsTo |
Dirichlet Process Gaussian Mixture Model
Infinite Gaussian Mixture Model |
| gptkbp:fittedBy |
gptkb:Expectation-Maximization_algorithm
|
| gptkbp:form |
Weighted sum of Gaussian densities
|
| gptkbp:hasModel |
Multimodal distributions
|
| https://www.w3.org/2000/01/rdf-schema#label |
Gaussian Mixture Model
|
| gptkbp:implementedIn |
gptkb:MATLAB
gptkb:TensorFlow_Probability gptkb:scikit-learn R |
| gptkbp:introduced |
gptkb:Karl_Pearson
|
| gptkbp:introducedIn |
1894
|
| gptkbp:limitation |
Sensitive to initialization
Assumes Gaussian components May converge to local optima |
| gptkbp:output |
Cluster assignments
Probability densities |
| gptkbp:parameter |
Mean
Mixing coefficient Covariance |
| gptkbp:relatedTo |
gptkb:Hidden_Markov_Model
gptkb:K-means_clustering Latent variable model Finite mixture model |
| gptkbp:requires |
Number of components
|
| gptkbp:usedIn |
Machine learning
Clustering Density estimation |
| gptkbp:visualizes |
Ellipses in feature space
|
| gptkbp:bfsParent |
gptkb:NVIDIA_cuMLGaussianMixture
gptkb:K-means gptkb:K-means_clustering gptkb:EM_algorithm |
| gptkbp:bfsLayer |
7
|