Approximation by ridge functions and neural networks with a bounded number of neurons
Vugar E. Ismailov · Applicable Analysis · 2014
In this paper, we consider the problem of approximation of continuous multivariate functions by neural networks with a bounded number of neurons in hidden layers. We prove the existence of single-hidden-layer networks with bounded number of neurons, which have approximation capabilities not worse than those of networks with arbitrarily many neurons. Our analysis is based on the properties of ridge functions.