This paper describes a new nonlinear projection method. The aim is to design a user-friendly method, tentativ ely as easy to use as the linear PCA (Principal Component Analysis). The method is based on CCA (Curvilinear Component Analysis). This paper presen ts tw o improvements with respect to the original CCA: a better beha vior in the projection of highly nonlinear databases (like spirals) and a complete automation in the choice of the parameters value.
Lee, J., Lendasse, A., Donckers, N., & Verleysen, M. (2000). A robust nonlinear projection method. Proceedings of ESANN 2000, European Symposium on Artificial Neural Networks, p. 13-20. https://hdl.handle.net/2078.5/225129