An artificial neural network is a biologically motivated computational model that consists of processing elements and connections between all of them. The structure of an artificial neuron is specified by inputs, containing weights bound to them; an inputfunction, which calculates the aggregated net input signal to a neuron that come from all its inputs; anactivation (signal) function, which computes the activation level of a neuron as a function of itsaggregated input signal and (possibly) of its previous state. An output signal equivalent to the activation valueis emitted through the output (the axon) of the neuron.