Bayesian noise model selection and system identification based on approximation of the evidence.
Jean-François GiovannelliAudrey GiremusPublished in: SSP (2014)
Keyphrases
- model selection
- marginal likelihood
- bayesian approaches
- bayesian learning
- cross validation
- hyperparameters
- bayesian model selection
- statistical inference
- bayesian methods
- regression model
- information criterion
- feature selection
- sample size
- mixture model
- variable selection
- statistical learning
- noise level
- posterior distribution
- parameter estimation
- motion segmentation
- machine learning
- model selection criteria
- bayesian information criterion
- missing data
- posterior probability
- leave one out cross validation
- error estimation
- automatic model selection
- selection criterion
- gaussian process
- generalization error
- generalization bounds
- closed form
- median filter
- maximum likelihood
- decision trees
- random sampling