abstract:In the mathematical theory of neural networks, the universal approximation theorem statesBalázs Csanád Csáji. Approximation with Artificial Neural Networks; Faculty of Sciences; Eötvös Loránd University, Hungary that a feed-forward network with a single hidden layer, the simplest form of the multilayer perceptron, containing a finite number of hidden neurons, is a universal approximator among continuous functions on compact subsets of Rn, under mild assumptions on the activation function.