Conjugate and natural gradient rules for BYY harmony learning on Gaussian mixture with automated model selection.
Jinwen MaBin GaoYang WangQianSheng ChengPublished in: Int. J. Pattern Recognit. Artif. Intell. (2005)
Keyphrases
- model selection
- unsupervised learning
- model selection criteria
- gaussian mixture
- selection criterion
- mixture model
- automatic model selection
- cross validation
- hyperparameters
- learning algorithm
- machine learning
- parameter estimation
- sample size
- learning problems
- learning rate
- feature selection
- dimensionality reduction
- supervised learning
- support vector
- statistical analysis
- reinforcement learning
- similarity measure
- natural gradient