A loss function approach to model selection in nonlinear principal components.

Webb, Andrew R. · Neural Netw · 1999

Where this comes from

Abstract

The nonlinear transformation of the input variables that characterises the first nonlinear principal component is modelled as a linear sum of radially-symmetric kernel functions. It is shown that the parameters of the variance maximising transformation may be obtained through the minimisation of a loss function measuring departure from homogeneity. An alternating least squares algorithm is given. This is used as the basis of a cross-validation routine for model selection.