We propose to take advantage of the advances in Artificial Intelligence and, in particular, Long Short-Term Memory Neural Networks (LSTM), to automatically infer model transformations from sets of input-output model pairs.
Models need to represent the reality as accurately as possible. Nevertheless, complex systems are subject to uncertainty something difficult to express with plain UML. We propose a way to represent uncertainty on software models. Our uncertainty values can then be propagated through model transformations to evaluate the impact on other parts of the system.