Parameterized online quasi-Newton training for high-nonlinearity function approximation using multilayer neural networks.
Hiroshi NinomiyaPublished in: IJCNN (2011)
Keyphrases
- function approximation
- multilayer neural networks
- quasi newton
- learning rate
- reinforcement learning
- learning algorithm
- radial basis function
- temporal difference
- newton method
- learning tasks
- supervised learning
- neural network training
- step size
- function approximators
- optimization method
- active learning
- optimization methods
- training algorithm
- machine learning algorithms
- optimization algorithm
- support vector machine
- training data