Comparison of neural models, off-line and on-line learning algorithms for a benchmark problem

This paper compares the application of different neural models multilayer perceptrons, radial basis functions and B-splines - for a benchmark problem, and illustrates the applicability of a common learning algorithm for all models considered. The learning algorithm is employed both for off-line training and for on-line model adaptation. In the latter case, a sliding window of past learning data is employed.