A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function

Abstract

The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can approximate an arbitrary continuous function provided that an unlimited number of neurons in a hidden layer is permitted. In this paper, we consider constructive approximation on any finite interval of $\mathbb{R}$ by neural networks with only one neuron in the hidden layer. We construct algorithmically a smooth, sigmoidal, almost monotone activation function $\sigma$ providing approximation to an arbitrary continuous function within any degree of accuracy. This algorithm is implemented in a computer program, which computes the value of $\sigma$ at any reasonable point of the real axis.

12 pages, 1 figure; to be published in Neural Computation; for associated SageMath worksheet, see http://sites.google.com/site/njguliyev/papers/sigmoidal

Cited by in corpus (4)

• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Approximation capability of two hidden layer feedforward neural networks with fixed weights
• A simple and efficient architecture for trainable activation functions
• Addressing common misinterpretations of KART and UAT in neural network literature