Stability analysis of neural networks

Neural networks can only be trained with a crisp and finite data set. Therefore stability analysis seems to be impossible. We propose a new method to show how stability for neural networks can be proven. We use fuzzy input and output data for the training process. After the learning phase the fuzzy network will be defuzzified. Using special properties of fuzzy neural networks the output behaviour can be estimated. This gives us the ability of proving stability for neural networks