A Study of Paraconsistent Artificial Neural Cell of Learning Applied as PAL2v Filter

作者：De Carvalho A Jr^*; Da Silva Filho J I; Mario M C; Blos M F; Cruz C M

来源：IEEE Latin America Transactions, 2018, 16(1): 202-209.

DOI：10.1109/tla.2018.8291474

• Paraconsistent Annotated Logic
• PAL2(v)Filter
• Paraconsistent Artificial Neural Cell of Learning

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 (PAN(cell)) 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 (LPAN(cell)) is a type of PAN(cell) whose 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 PAL2(v)Filter. The objective of this paper is to study the PAL2(v)Filter by simulations and evaluate the differences when using two types of LPAN(cell). The first LPAN(cell) features an output that represents the degree of evidence and the second LPAN(cellr) is characterized by a value in the output which is extracted the effect of contradiction.

• 出版日期2018-1