- Universal approximation theorem
In the mathematical theory of neural networks, the universal approximation theorem states that the standard multilayer feed-forward network with a single hidden layer that contains finite number of hidden neurons, and with arbitrary activation function are universal approximators on a compact subset of Rn.
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.)
Let φ(·) be a nonconstant, bounded, and monotonically-increasing continuous function. Let Im denote the m-dimensional unit hypercube [0,1]m. The space of continuous functions on Im0 is denoted by C(Im). Then, given any function f ∈ C(Im) and є > 0, there exist an integer N and sets of real constants αi, bi ∈ R, wi ∈ Rm, where i = 1, ..., N such that we may define:
- | F(x) − f(x) | < ε
- ^ Balázs Csanád Csáji. Approximation with Artificial Neural Networks; Faculty of Sciences; Eötvös Loránd University, Hungary
- ^ a b Cybenko., G. (1989) "Approximations by superpositions of sigmoidal functions", Mathematics of Control, Signals, and Systems, 2 (4), 303-314
- ^ a b Kurt Hornik (1991) "Approximation Capabilities of Multilayer Feedforward Networks", Neural Networks, 4(2), 251–257
- ^ Haykin, Simon (1998). Neural Networks: A Comprehensive Foundation, Volume 2, Prentice Hall. ISBN 0132733501.
- ^ Hassoun, M. (1995) Fundamentals of Artificial Neural Networks MIT Press, p. 48
Wikimedia Foundation. 2010.