Process Discovery is an unsupervised learning problem with the task of discovering a graph-based model from sequences (or graphs) of event data that describes the data best. Generative Adversarial Neural Networks (GANNs) are a type of neural networks used to learn structures in an unsupervised fashion. The objective of this project is to explore the potential to apply GANNs for process discovery. Besides surveying the state of the art GANNs, the project will require generation training and evaluating existing techniques GANNs to discover process models, and to compare the outcomes to models produced by current algorithm-based process discovery techniques.
Contact: Dr. Dirk Fahland.