翻訳と辞書
Words near each other
・ Universal Air Travel Plan
・ Universal Airlines
・ Universal Airlines (Guyana)
・ Universal Airlines (United States)
・ Universal Alcatel
・ Universal algebra
・ Universal algebraic geometry
・ Universal Alliance
・ Universal allocation per child
・ Universal American
・ Universal American Flea Ship
・ Universal angiomatosis
・ Universal Animation Studios
・ Universal Annihilation Army Warstar
・ Universal annuity system
Universal approximation theorem
・ Universal asynchronous receiver/transmitter
・ Universal Atomic 4
・ Universal Attractions Agency
・ Universal Audenried Charter High School
・ Universal Audio
・ Universal Audio (album)
・ Universal Audio (company)
・ Universal Audio Architecture
・ Universal Avenue
・ Universal Aviation Corporation
・ Universal Avionics
・ Universal background check
・ Universal Backlot Series
・ Universal Ballet


Dictionary Lists
翻訳と辞書 辞書検索 [ 開発暫定版 ]
スポンサード リンク

Universal approximation theorem : ウィキペディア英語版
Universal approximation theorem
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:

Let \varphi(\cdot) be a nonconstant, bounded, and monotonically-increasing continuous function. Let I_m denote the ''m''-dimensional unit hypercube ()^m. The space of continuous functions on I_m is denoted by C(I_m). Then, given any function f\in C(I_m) and \varepsilon>0, there exists an integer N and real constants v_i,b_i\in\mathbb, where i=1,\cdots,N such that we may define:
:
F( x ) =
\sum_^ v_i \varphi \left( w_i^T x + b_i\right)

as an approximate realization of the function f where f is independent of \varphi; that is,
:
| F( x ) - f ( x ) | < \varepsilon

for all x\in I_m. In other words, functions of the form F(x) are dense in C(I_m).

It obviously holds replacing I_m with any compact subset of \mathbb^m.

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
翻訳と辞書 : 翻訳のためのインターネットリソース

Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.