Design of Multi-Layer Neural Networks for Accurate Identification of Nonlinear Mappings
Edilberto Pereira Teixeira, Kenneth A. Loparo, Fernando A. C. Gomide · 1991
Guidelines for the design of multi-layer neural networks for the identification of nonlinear mappings are considered in this work. Since nonlinear mappings can be approximated by a one hidden layer neural network, an approach to determine the sufficient number of hidden layer nodes to achieve a global minima of the identification error function is considered.