Proving properties of neural networks with graph transformations

Graph transformations offer a unifying framework to formalize neural networks together with their corresponding training algorithms. It is straightforward to describe also topology changing training algorithms with the help of these transformations. One of the benefits using this formal framework is the support for proving properties of the training algorithms. A training algorithm for probabilistic neural networks is used as an example to prove its termination and correctness on the basis of the corresponding graph rewriting rules