Superkernels for RBF Networks Initialization (Short Paper)

Abstrakt

One of the basic tasks solved using artificial neural networks is the regression task. In its canonical form, one seeks for adjusting network’s parameters so that its response on input training data fits the desired outputs reasonably well. Training data {xi, yi}n i=1, n ∈ N consists of points from Rd+1 Euclidean space, i.e., xi ∈ Rd, yi ∈ R. The quality of the fit is typically measured in terms of the mean integrated squared error (MISE). Various regularization techniques are considered to prevent from overfitting. Optimal setting of parameters can be specified analytically in the linear model (linear computational units), however, for the nonlinear units, the network’s parameters are set using different variants of stochastic optimization [1].