Fisher Scoring and a Mixture of Modes Approach for Approximate Inference and Learning in Nonlinear State Space Models.
Thomas BriegelVolker TrespPublished in: NIPS (1998)
Keyphrases
- prior information
- prior knowledge
- structured prediction
- approximate inference
- state space
- dynamic bayesian networks
- graphical models
- learning algorithm
- parameter estimation
- reinforcement learning
- training data
- exact inference
- model selection
- active learning
- latent variables
- segmentation method
- maximum margin
- bayesian methods
- undirected graphical models
- state variables
- incremental learning
- bayesian framework
- particle filter
- learning process
- similarity measure
- image processing