Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
: A new supervised learning procedure for training RBF networks is proposed. It uses a pair of parallel running Kalman filters to sequentially update both the output weights and th...
Efficient multi-scale manifold reconstruction from point clouds can be obtained through the Hierarchical Radial Basis Functions (HRBF) network. An online training procedure for HRB...
Francesco Bellocchio, Stefano Ferrari, Vincenzo Pi...
Scatterograms of the images of training set vectors in the hidden space help to evaluate the quality of neural network mappings and understand internal representations created by t...