“…After the new data {(x (n) , f NEW (n) ); n = 1, 2, …, N} are available, the new coefficients {α NEW,k ; k = 1, 2, ..., K} can be modeled by the probability density function pdf(α NEW | f NEW ) (i.e., the posterior distribution) in (7). Depending on the shape of the posterior distribution pdf(α NEW | f NEW ), the new coefficients {α NEW,k ; k = 1, 2, ..., K} do not take all possible values with equal probability.…”