“…It has only one hidden layer, which has been proven satisfactory for two-variable function approximation. 20 Indices: “in”, “h”, and “o”, in this figure, stand for input, hidden, and output, respectively. For the set of weights, w ( k, l ), connecting the input and the hidden layer we have: k = 1, 2, …, m in , l = 1, 2, …, m h , while for the set connecting the hidden and output layer we have: k = 1,2, …, m h , l = 1,2, …, m o .…”