Skip to Main content Skip to Navigation
New interface
Journal articles

Approximation with activation functions and applications

Abstract : Function 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.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02543988
Contributor : Radhia Bessi Connect in order to contact the contributor
Submitted on : Friday, April 30, 2021 - 11:55:21 AM
Last modification on : Wednesday, August 31, 2022 - 12:14:23 PM

File

Approximate_ActivationV5.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Radhia Bessi. Approximation with activation functions and applications. Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, 2021, Volume 32 - 2019 - 2021 (32), ⟨10.46298/arima.6464⟩. ⟨hal-02543988v5⟩

Share

Metrics

Record views

950

Files downloads

1174