Data transformation for learning in feedforward neural nets

The authors target the problem of curve fitting on data samples for the purpose of subsequent interpolation. This is what backpropagation was developed for but its dependency on initial conditions and net topology affects its robustness. Here the authors present a different method which is based on an analysis of possible properties of the internal representations developed as a result of learning. Thus they introduce some additional constraints concerning direct control on internal representations. This method incorporates properties of supervised as well as unsupervised learning in the fitting problem