It is shown in this paper that if the hidden layer units take a sinusoidalactivation function,the optimum weights of the three-layer feedforward neural networkc
The method of automatically building 3-D molecular structure ofmacrorings is proposed in the paper.The method can build the 3-D models ofmacrorings full automat
Two diagnostics are presented for the transformation of explanatoryvariables in regression.One is based on the likelihood displacement proposed by Cookand Weisb