In general, an RBF network can be described as constructing global approximations to functions using combinations
of basic functions centered around weight vectors. In fact, it has been shown that RBF networks are universal
function approximators. Practically, however, the approximated function must be smooth and piecewise
continuous. Consequently, although RBF networks can be used for discrimination and classification tasks, binary
pattern classification functions that are not piecewise continuous (e.g., parity) pose problems for RBF networks
Thus, RB The RBF network used in this work is given in Figure 1. It consists of an input layer, one hidden layer
and an output layer.