Minimal training set size estimation for neural network-based function approximation

A new approach to the problem of n-dimensional continuous and sampled-data function approximation using a two-layer neural network is presented. The generalized Nyquist theorem is introduced to solve for the optimum number of training examples in n-dimensional input space. Choosing the smallest but still sufficient set of training vectors results in a reduced learning time for the network. Analytical formulas and algorithm for training set size reduction are developed and illustrated by two-dimensional data examples.< >