Implementation of probabilistic automata in weightless neural networks

Abstract

The objective of this paper is to analyze the practical viability of the theoretical results concerning the relationship between a class of weightless neural networks, known as general single-layer sequential weightless neural networks (GSSWNNs), and the probabilistic automata (PA). This study was based on the theoretical model development by de Souto (1999). This model shows the computational equivalence between the GSSWNNs and PAs. However, in order to develop a practical implementation, it is important to deal with the questioning of whether restrictions on the original theoretical results are necessary.