A Combined Representation to Refine the Knowledge Using a Neuro-Symbolic Hybrid System applied in a Problem of Apple Classification

An Enhanced Petri Net Model to Verify and Validate a Neural-Symbolic Hybrid System

“…Neural-Symbolic Hybrid Systems are systems based on artificial neural networks that also interact with symbolic components (Cloete & Zurada, 2000). These types of systems integrate the connectionist and symbolic knowledge, in such a way that the knowledge contained in each one of these is complemented (Cruz, Reyes, Vergara, Perez, & Montes, 2005;Cruz, Reyes, Vergara, & Pinto, 2006;Negnevitsky, 2005;Santos, 1998).…”

“…An anomaly is referred to common fault patterns according to an analysis technique (Ramirez & De Antonio, 2007;Tsai, Vishnuvajjala, & Zhang, 1999). This KB can contain errors due to: 1) the existence of several human experts providing their experiences in the application field 2) the inserted knowledge can not be represented properly because of communication problems between human experts and the knowledge engineer, 3) the information may be missed during knowledge insertion due to matching of same one to the neural network, 4) The base of examples might be redundant due to a bad selection of samples, and 5) information may be missed or gained during the integration process of numerical and symbolic knowledge (Cruz, Reyes, Vergara, & Pinto, 2006;He, Chu, & Yang, 2003;Santos, 1998;Villanueva, Cruz, Reyes, & Benítez, 2006). The anomalies that can be found in a KB are shown in Figure 2.…”

“…Neural-Symbolic Hybrid Systems have received great attention and they have been used in application areas where the existence of faults can be expensive, such as engineering, manufacturing, science, business (Cruz, Reyes, Vergara, Perez, & Montes, 2005;Cruz, Reyes, Vergara, & Pinto, 2006;Santos, 1998) and cognitive informatics and cognitive computing (Wang, 2003(Wang, , 2008. The NSHS combine symbolic knowledge (rules or frames, mainly) and connectionist (neural networks).…”