GENERALIZATION STUDY FOR A ROBUST ESTIMATION METHOD OF NEURAL NETS
一种神经网络稳健估计方法的推广性研究

In this paper, the Cauchy function is taken as a new target function of neural network accordings to the robustness theorem of statistics. Under the same network parameter conditions the BP net is trained using both mean squares and Cauchy target function first, then the net is tested by data sets including small Gaussian noises and outliers separately. Simulation results indicate that the network has both faster convergence speed and better performance against outliers after learning with robust target function.