Neural networks using a logistics sigmoid function: linear classifier bounds and global nonattainability
Anthony V. Fiacco, Jiming. Liu · Optimization · 1995
Simple examples clearly demonstrate that highly consistent data lead to solution nonattainability, in neural networks utilizing a logistics sigmoid function. Solution attainability requires a high degree of inconsistency. Bounds are obtained on the optimal value of the mean-square error of a one-layer neural network, in terms of the minimum number of misclassifications obtained from three linear classification problems, and conditions are given that imply solution attainability and nonattainability