Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi-Step-Ahead Predictions.
Artem N. ChernodubPublished in: CoRR (2016)
Keyphrases
- feed forward neural networks
- extended kalman filter
- back propagation
- training algorithm
- neural network
- artificial neural networks
- multi layer
- feed forward
- hidden layer
- kalman filter
- activation function
- kalman filtering
- multilayer perceptron
- feedforward neural networks
- state estimation
- fuzzy logic
- bp neural network
- basis functions
- neural nets
- training process
- learning algorithm
- estimation accuracy
- computer simulation
- estimation process
- machine learning
- error rate
- support vector machine
- recurrent neural networks
- training set
- artificial intelligence