抄録
In this paper, Universal Learning Networks with Branch Control (ULNs with BC) is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment means to multiply the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are done in ULNs with BC, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BC is applied to a function approximation problem and a two-spirals problem. The simulation results show that ULNs with BC exhibits better performances than the conventional neural networks with comparable complexity.
