The comparison between BENN and IENN shows that IENN has faster convergence rate than BENN.
On the lower side of Figures 4(a) and 4(b), when BENN and IENN have the same number of iteration; to achieve the same SSE(k), IENN needs less neurons in hidden layer than BENN.
The Volterra-Laguerre (VL) model  and the Chebyshev neural network (CNN) model [17, 23, 24] are introduced to be compared with the BENN and IENN model.
It can be seen in Figure 5 and Table 1 that IENN is the most accurate model among four models.
The spectrum errors of BENN and IENN model are stable; under the same conditions, the spectrum error of BENN is 0.011 dB, and IENN is 4.92 x [10.sup.-6] dB.
In the same conditions of the number of hidden neurons N = 25 and the iteration step [K.sub.max] = 50, the time domain errors of both IENN and BENN model are basically the same and the final maximum transient error of BENN is 1.74 x [10.sup.-5] V, while it is 1.83 x [10.sup.-5] V in IENN.
The spectrum errors of BENN and IENN model are stable; under the same simulation conditions, the maximum spectrum error of BENN is 4.66 x [10.sup.-6] dB, and IENN is 4.92 x [10.sup.-6] dB.
Under the same conditions that the number of hidden neurons is 25 and the iteration step is 50, IENN model is more precise than BENN model.
The comparison among four behavioral models under the condition of different input signals and the same simulation parameters shows that the proposed IENN model is the most accurate model for analyzing the nonlinearity and memory effect of the CDPAs in both time domain and frequency domain.
In this paper, a behavioral modeling based on IENN is proposed to describe the nonlinearity and memory effect of CDPAs.