On Derivation of MLP Backpropagation from the Kelley-Bryson Optimal-Control Gradient Formula and Its Application.
Eiji MizutaniStuart E. DreyfusKenichi NishioPublished in: IJCNN (2) (2000)
Keyphrases
- optimal control
- back propagation
- multilayer perceptron
- artificial neural networks
- neural network
- policy gradient
- feed forward
- dynamic programming
- control problems
- bp algorithm
- training algorithm
- hidden layer
- neural nets
- feed forward neural networks
- control strategy
- fuzzy logic
- learning algorithm
- optimal control problems
- multilayer perceptron neural network
- bp neural network
- backpropagation algorithm
- feedforward neural networks
- multi layer perceptron
- activation function
- connection weights
- backpropagation neural network
- lyapunov function
- rbf network
- radial basis
- control law
- linear quadratic
- backpropagation neural networks
- reinforcement learning
- neural network ensemble
- fuzzy artmap
- gradient method
- recurrent neural networks
- artificial intelligence