Generating workflow graphs using typed genetic programming
Tomáš Křen, Martin Pilát, Klára Pešková, Roman Neruda · ASEP · 2015
In this paper we further develop our research line of chaining several preprocessing methods with classifiers [1], by generating the complete workflow schemes. These schemes, represented as directed acyclic graphs (DAGs), contain computational intelligence methods together with preprocessing algorithms and various methods of combining them into ensembles.