Researches on artificial neural network models have shown that the method used to initialize and estimate weights bias always determines rate at which will converge how efficient model perform. Although there are several methods can be bias, Bayesian approach is widely considered as a more for modelling networks because it easily compute inverses of covariance matrices with high dimension other...

We study the problem of constructing rank-1 lattice rules which have good bounds on the “weighted star discrepancy”. Here the non-negative weights are general weights rather than the product weights considered in most earlier works. In order to show the existence of such good lattice rules, we use an averaging argument, and a similar argument is used later to prove that these lattice rules may ...

abstract according to the adventages of passive radars they have been reconsidered recently due to development of signal processing technology. in the field of sea targets detection using passive radar few research have been reported. this paper presents a new method to detect sea targets using adaptive filter weights variation model and using the fact that the radar cross section of sea target...