Using a Helper FFN to Represent the Cost Function for Training DRNN's by Gradient Descent.
Roelof K. BrouwerPublished in: HIS (2002)
Keyphrases
- cost function
- neural network
- training algorithm
- global minimum
- air fuel ratio
- objective function
- feed forward neural networks
- step size
- training set
- training phase
- machine learning
- multi layer perceptron
- training samples
- back propagation
- level set
- artificial neural networks
- stochastic gradient descent
- decision trees