Neural Networks And Rational McNaughton Functions
Paolo Amato, Antonio Di Nola and Brunella Gerla
In this paper we shall describe a correspondence between Rational McNaughton functions (as truth table of Rational Lukasiewicz formulas)and neural networks in which the activation function is the truncated identity and synaptic weights are rational numbers. On one hand to have a logical representation (in a given logic) of neural networks could widen the interpretability, amalgamability and reuse of these objects. On the other hand, neural networks could be used to learn formulas from data and as circuital counterparts of (functions represented by) formulas.