|
In the mathematical theory of artificial neural networks, the universal approximation theorem states〔Balázs Csanád Csáji. Approximation with Artificial Neural Networks; Faculty of Sciences; Eötvös Loránd University, Hungary〕 that a feed-forward network with a single hidden layer containing a finite number of neurons (i.e., a multilayer perceptron), can approximate continuous functions on compact subsets of Rn, under mild assumptions on the activation function. The theorem thus states that simple neural networks can ''represent'' a wide variety of interesting functions when given appropriate parameters; it does not touch upon the algorithmic learnability of those parameters. One of the first versions of the theorem was proved by George Cybenko in 1989 for sigmoid activation functions.〔Cybenko., G. (1989) ("Approximations by superpositions of sigmoidal functions" ), ''Mathematics of Control, Signals, and Systems'', 2 (4), 303-314〕 Kurt Hornik showed in 1991〔Kurt Hornik (1991) "(Approximation Capabilities of Multilayer Feedforward Networks )", ''Neural Networks'', 4(2), 251–257. 〕 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, only the single output case will be shown. The general case can easily be deduced from the single output case. == Formal statement == The theorem〔〔〔Haykin, Simon (1998). ''Neural Networks: A Comprehensive Foundation'', Volume 2, Prentice Hall. ISBN 0-13-273350-1.〕〔Hassoun, M. (1995) ''Fundamentals of Artificial Neural Networks'' MIT Press, p. 48〕 in mathematical terms:
It obviously holds replacing with any compact subset of . 抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)』 ■ウィキペディアで「Universal approximation theorem」の詳細全文を読む スポンサード リンク
|