Verification and validation of a Neural-Symbolic Hybrid System using an enhanced Petri net

As the neural-symbolic hybrid systems (NSHS) gain acceptance, it increases the necessity to guarantee the automatic validation and verification of the knowledge contained in them. In the past, such processes were made manually. In this paper, an enhanced Petri net model is presented to the detection and elimination of structural anomalies in the knowledge base of the NSHS. In addition, a reachability model is proposed to evaluate the obtained results of the system versus the expected results by the user. The validation and verification method is divided in two stages: 1) it consists of three phases: rule normalization, rule modeling and rule verification. 2) It consists of three phases: rule modeling, dynamic modeling and evaluation of results. Such method is useful to ensure that the results of a NSHS are correct. Examples are presented to demonstrate the effectiveness of the results obtained with the method.