Ensemble Kalman Filter Optimizing Deep Neural Networks: An Alternative Approach to Non-performing Gradient Descent.
Alper YegenogluKai KrajsekSandra Díaz-PierMichael HertyPublished in: LOD (2) (2020)
Keyphrases
- kalman filter
- neural network
- kalman filtering
- state estimation
- object tracking
- extended kalman filter
- state space model
- neural network ensemble
- particle filter
- artificial neural networks
- objective function
- target tracking
- akaike information criterion
- pattern recognition
- training data
- back propagation
- neural network model
- data association
- radial basis function
- bayesian filtering
- multilayer perceptron
- mean shift
- fuzzy logic
- robust tracking
- prediction accuracy
- feature selection