Universal approximation theorem: Difference between revisions

Revision as of 04:10, 28 July 2008

Revision as of 16:11, 11 December 2008

Line 2:

<noinclude>

In mathematics, the '''universal approximation theorem''' states<ref>Balázs Csanád Csáji. Approximation with Artificial Neural Networks; Faculty of Sciences; Eötvös Loránd University, Hungary</ref> that the standard multilayer feed-forward network with a single hidden layer that contains finite number of hidden [[neuron]]s, and with arbitrary activation function are universal approximators inon ''C''(Rm)a compact subset of <math>\mathbb{R}^n</math>. Kurt Hornik (1991) showed that it is not the specific choice of the activation function, but rather the multilayer feedforward architecture itself which gives neural networks the potential of being universal approximators. The output units are always assumed to be linear. For notational convenience we shall explicitly formulate our results only for the case where there is only one output unit. (The general case can easily be deduced from the simple case.) The theorem<ref>G. Cybenko. Approximations by superpositions of sigmoidal functions. Mathematics of Control, Signals, and Systems, 2:303–314, 1989.</ref><ref>

Kurt Hornik: Approximation Capabilities of Multilayer Feedforward Networks.

Neural Networks, vol. 4, 1991.</ref><ref>Haykin, Simon (1998). Neural Networks: A Comprehensive Foundation, 2, Prentice Hall. ISBN 0132733501.</ref> in mathematical terms: