Dynamic sample size selection based quasi-Newton training for highly nonlinear function approximation using multilayer neural networks.

Hiroshi Ninomiya

Published in: IJCNN (2013)

Keyphrases

sample size
function approximation
multilayer neural networks
reinforcement learning
learning rate
learning algorithm
model selection
learning tasks
radial basis function
upper bound
worst case
training data
training set
artificial neural networks
basis functions
neural network training