State, global and local parameter estimation using local ensemble Kalman filters: applications to online machine learning of chaotic dynamics.
Quentin MalarticAlban FarchiMarc BocquetPublished in: CoRR (2021)
Keyphrases
- parameter estimation
- kalman filter
- machine learning
- model selection
- chaotic dynamics
- state estimation
- maximum likelihood
- least squares
- markov random field
- parameter estimation algorithm
- em algorithm
- feature selection
- random fields
- global motion
- kalman filtering
- learning algorithm
- expectation maximization
- state space
- chaotic neural network
- parameter estimates
- object tracking
- neural network
- cellular automata
- particle filtering
- optical flow