Training under achievement quotient criterion

The cost function of the training algorithm plays a very important role especially in applications of neural networks (NNs) to signal processing. In this paper, a new training algorithm under the achievement quotient criterion is proposed for preserving important information such as edges and envelopes. The experiments to reduce noise from natural and medical images were performed. By comparisons with the standard backpropagation algorithm, it has been shown that the NNs trained by the proposed training have a desirable characteristic: the performance on preserving the edges and fine structures of objects is clearly superior