FOURIER NEURAL NETWORKS: A COMPARATIVE STUDY
| dc.contributor.author | Zhumekenov, Abylay | |
| dc.contributor.author | Uteuliyeva, Malika | |
| dc.contributor.author | Takhanov, Rustem | |
| dc.contributor.author | Assylbekov, Zhenisbek | |
| dc.contributor.author | Castro, Alejandro J. | |
| dc.date.accessioned | 2022-07-14T08:49:04Z | |
| dc.date.available | 2022-07-14T08:49:04Z | |
| dc.date.issued | 2019 | |
| dc.description.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. | en_US |
| dc.identifier.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 | en_US |
| dc.identifier.uri | http://nur.nu.edu.kz/handle/123456789/6432 | |
| dc.language.iso | en | en_US |
| dc.publisher | arxiv | en_US |
| dc.rights | Attribution-NonCommercial-ShareAlike 3.0 United States | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/us/ | * |
| dc.subject | Type of access: Open Access | en_US |
| dc.subject | neural network architectures | en_US |
| dc.subject | Fourier neural networks | en_US |
| dc.title | FOURIER NEURAL NETWORKS: A COMPARATIVE STUDY | en_US |
| dc.type | Article | en_US |
| workflow.import.source | science |