Improving the Learning Speed in 2-Layered LSTM Network by Estimating the Configuration of Hidden Units and Optimizing Weights Initialization.
Débora C. CorrêaAlexandre L. M. LevadaJosé Hiroki SaitoPublished in: ICANN (1) (2008)
Keyphrases
- hidden units
- learning speed
- rbf network
- feed forward neural networks
- activation function
- radial basis function
- neural network
- back propagation
- nonlinear functions
- recurrent neural networks
- multi layer
- learning algorithm
- hidden layer
- rbf neural network
- artificial neural networks
- feed forward
- basis functions
- training algorithm
- multilayer perceptron
- optimization methods
- neural nets
- rule base
- probabilistic model
- training data