Computational Intelligence (CI), originally represented by the three subjects of Evolutionary Computation (EC), Fuzzy Logic (FL) and Neural Networks (NNs), has significantly evolved to date and reached high levels of hybridisation and complexity. Starting from fuzzy neural or genetic systems, to the more recent computational frameworks such as deep learning and natural learning processing, the subject of CI has widened and grown to traverse many disciplines and application domains. At the same time, this growth has made evident the lack of consistent theoretical knowledge based on which practitioners could control CI systems and have them express their full potential while addressing the real-world scenarios.

This means that in practice, high performance and quality of results are only achievable if theoretical CI community concentrates on filling the gaps in theoretical knowledge and CI practitioners put latest developments to use in their applications to address practical problems. Thus, through informed use of CI methods synergetically tailored to the problem at hand, on the base of the available theoretical knowledge, practitioners can suggest novel theoretically backed up solutions to benefit their applications. Indeed, following this research philosophy, ad-hoc CI solutions are currently being successfully created in the most heterogeneous fields, such as e.g. finance, medicine, precision agriculture and aviation, as well as in numerous information systems.