An approximation of nonlinear discriminant analysis by multilayer neural networks
Hideki Asoh, N. Otsu · 1990
An architecture of a four-layer (two hidden layers) neural network is proposed in order to approximate nonlinear discriminant analysis. The architecture is based on a previously observed relationship between multilayer neural networks and back-propagation (least mean squared error) learning and nonlinear data analysis methods. The effectiveness of the architecture has been verified experimentally. It is shown that the networks have a much stronger capability of class separation than the usual linear discriminant analysis method