Towards neural-symbolic integration: the evolutionary neural logic networks

This work presents the application of a new methodology for the production of neural logic networks into two real-world problems from the medical domain. Namely, we apply grammar guided genetic programming using cellular encoding for the representation of neural logic networks into population individuals. The application area is consisted of the diagnosis of diabetes and the diagnosis of the course of hepatitis patients. The system is proved able to generate arbitrarily connected and interpretable evolved solutions leading to potential knowledge extraction.