International audienceFunction approximation arises in many branches of applied mathematics and computer science, in particular in numerical analysis, in finite element theory and more recently in data sciences domain. From most common approximation we cite, polynomial, Chebychev and Fourier series approximations. In this work we establish some approximations of a continuous function by a series of activation functions. First, we deal with one and two dimensional cases. Then, we generalize the approximation to the multi dimensional case. Examples of applications of these approximations are: interpolation, numerical integration, finite element and neural network. Finally, we will present some numerical results of the examples above.La théori...
In this paper, we develop a constructive theory for approximating absolutely continuous functions ...
AbstractLet s ≥ d ≥ 1 be integers, 1 ≤ p < ∞. We investigate the degree of approximation of 2π-perio...
Wavelet functions have been successfully used in many problems as the activation function of feedfor...
International audienceFunction approximation arises in many branches of applied mathematics and comp...
The theory of functional approximation has numerous applications in sciences and industry. This thes...
For purposes of evaluation and manipulation, mathematical functions f are commonly replaced by appro...
Approximation theory studies the process of approaching arbitrary functions by simple func-tions dep...
We compare activation functions in terms of the approximation power of their feedforward nets. We co...
We compare activation functions in terms of the approximation power of their feedforward nets. We co...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Abstract. We prove that neural networks with a single hidden layer are capable of providing an optim...
AbstractA nontraditional approach is presented to the approximation of a one-dimensional function de...
AbstractWe study an approximation of a multivariate function f by an operator of the form ∑i=1NT˜r[f...
In this paper, we develop a constructive theory for approximating absolutely continuous functions ...
AbstractLet s ≥ d ≥ 1 be integers, 1 ≤ p < ∞. We investigate the degree of approximation of 2π-perio...
Wavelet functions have been successfully used in many problems as the activation function of feedfor...
International audienceFunction approximation arises in many branches of applied mathematics and comp...
The theory of functional approximation has numerous applications in sciences and industry. This thes...
For purposes of evaluation and manipulation, mathematical functions f are commonly replaced by appro...
Approximation theory studies the process of approaching arbitrary functions by simple func-tions dep...
We compare activation functions in terms of the approximation power of their feedforward nets. We co...
We compare activation functions in terms of the approximation power of their feedforward nets. We co...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Quand on veut évaluer ou manipuler une fonction mathématique f, il est fréquent de la remplacer par ...
Abstract. We prove that neural networks with a single hidden layer are capable of providing an optim...
AbstractA nontraditional approach is presented to the approximation of a one-dimensional function de...
AbstractWe study an approximation of a multivariate function f by an operator of the form ∑i=1NT˜r[f...
In this paper, we develop a constructive theory for approximating absolutely continuous functions ...
AbstractLet s ≥ d ≥ 1 be integers, 1 ≤ p < ∞. We investigate the degree of approximation of 2π-perio...
Wavelet functions have been successfully used in many problems as the activation function of feedfor...