FOURIER NEURAL NETWORKS: A COMPARATIVE STUDY

Loading...
Thumbnail Image

Date

2019

Authors

Zhumekenov, Abylay
Uteuliyeva, Malika
Takhanov, Rustem
Assylbekov, Zhenisbek
Castro, Alejandro J.

Journal Title

Journal ISSN

Volume Title

Publisher

arxiv

Abstract

We review neural network architectures which were motivated by Fourier series and integrals and which are referred to as Fourier neural networks. These networks are empirically evaluated in synthetic and real-world tasks. Neither of them outperforms the standard neural network with sigmoid activation function in the real-world tasks. All neural networks, both Fourier and the standard one, empirically demonstrate lower approximation error than the truncated Fourier series when it comes to approximation of a known function of multiple variables.

Description

Keywords

Type of access: Open Access, neural network architectures, Fourier neural networks

Citation

Uteuliyeva, M., Zhumekenov, A., Takhanov, R., Assylbekov, Z., Castro, A. J., & Kabdolov, O. (2020). Fourier neural networks: A comparative study. Intelligent Data Analysis, 24(5), 1107–1120. https://doi.org/10.3233/ida-195050

Collections