Interval arithmetic backpropagation

We present a new extension of the Backpropagation learning algorithm by using interval arithmetic. The proposed algorithm represents a generalization of Backpropagation and contains Backpropagation like a particular case. This new algorithm permits the use of training samples and targets which can be indistinctly points and intervals. Among the possible applications of this algorithm, we report its usefulness to integrate expert\u27s knowledge and experimental samples and also its ability to handle \u27don\u27t care attributes\u27 in a simple and natural way in comparison with Backpropagation. It also adds flexibility to the codification of inputs and outputs