A tool to implement probabilistic automata in RAM-based neural networks

In previous works, it was proved that General Single-layer Sequential Weightless Neural Networks (GSSWNNs) are equivalent to probabilistic automata. The class of GSSWNNs is an important representative of the research on temporal pattern processing in Weightless Neural Networks or RAM-based neural networks. Some of the proofs provide an algorithm to map any probabilistic automaton into a GSSWNN. They not only allows the construction of any probabilistic automaton, but also increases the class of functions that can be computed by the GSSWNNs. For instance, these networks are not restricted to finite-state languages and can now deal with some context-free languages. In this paper, based on such algorithms, we employ the probability interval method and Java to develop a tool to transform any PA into a GSSWNNs (including the probabilistic recognition algorithm). The probability interval method minimizes the round-off errors that occur while computing the probabilities.