A Study of Paraconsistent Artificial Neural Cell of Learning Applied as PAL2v Filter
A. de Carvalho, João Inácio da Silva Filho, Maurício Conceição Mário, Maurício Fontoura Blos, Clovis Misseno da Cruz · IEEE Latin America Transactions · 2018
The Paraconsistent Annotated Logic (PAL) is one type of non-classical logics that, differently than classical logic, allows the processing of contradictory signals in its theoretical structure. The Paraconsistent Artificial Neural Cell (PANcell) is the basic block of a set of algorithms that utilizes the interpretation of the lattice of the Paraconsistent Annotated Logic with annotation of two values (PAL2v). The Paraconsistent Artificial Neural Cell of Learning (LPANcell) is a type of PANcellwhose behavior is to learn any real value applied to its input, within a normalized closed range. This cell can be used in signal analysis, processing, average estimator and as a filter, called PAL2vFilter. The objective of this paper is to study the PAL2vFilter by simulations and evaluate the differences when using two types of LPANcell. The first LPANcellfeatures an output that represents the degree of evidence and the second LPANcellris characterized by a value in the output which is extracted the effect of contradiction.