Training a Paraconsistent Learning Artificial Neural Cell (CNAPap) using Microsoft Excel Rodney Gomes da Silva, João Inácio da Silva Filho, Dorotéa Vilanova Garcia

Abstract

Research and studies on Paraconsistent Logic (LP) have aroused great interest among specialists in the area of ​​industrial automation and other areas, especially in health, and, in this case, the application methods of this logic are quite promising. This work presents a way of applying the algorithm of the Artificial Neural Cell Paraconsistent Learning (CNAPap), which originated from the Annotated Paraconsistent Logic with Two-Value Annotation (LPA2v). The CNAPap algorithm was configured to operate in an application software where training was done to study how a neural cell learns more quickly through its iterations. The results of this study demonstrated that various controls applied in Artificial Intelligence with Paraconsistent Analysis Networks composed of CNAPap can be simulated and tested with the resources of an application software before a real application.