is passed through the network and the measured output of the neural network is y(n). The error signal, ej(n), instantaneous error energy, Ej(n), and total error, E(n), is given by: ej(n) = dj(n) − yj(n), Ej(n) = 1 2 e2 j (n), E(n) = C j=1 Ej(n) = 1 2 C j=1 e2 j (n) where we denoted E(n) and ej(n) as EQ01 and EQ02, respectively. The Total Error Overall Samples Eav(N) = 1 N N n=1 E(n) = 1 2N N n=1 C j=1 e2 j (n) 19 / 47