On the conditions of outer-supervised feedforward neural networks for null cost learning
De-Shuang Huang · 2003
This paper investigates, from the viewpoint of linear algebra, the local minima of least square error cost functions defined at the outputs of outer-supervised feedforward neural networks (FNN). For a specific case, we also show that those spacedly colinear samples (probably output by the final hidden layer) will be easily separated with null-cost error function even if the condition M/spl ges/N is not satisfied. In the light of these conclusions we shall give a general method for designing a suitable architecture network to solve a specific problem.