A Radial Base Localized Distribution for Deterministic Function Approximation Neural Networks. | ||||
MEJ- Mansoura Engineering Journal | ||||
Article 8, Volume 23, Issue 3, September 1998, Page 1-9 PDF (103.49 K) | ||||
Document Type: Research Studies | ||||
DOI: 10.21608/bfemu.2021.149971 | ||||
View on SCiNiTO | ||||
Authors | ||||
K. A. El-Serafi* ; K. Z. Moustafa | ||||
Electrical Engineering Department ., Suez Canal University., Port-Said., Egypt. | ||||
Abstract | ||||
In this work, we investigate the possibility of reducing the computational requirements of the deterministic nearal network function approximator, DEFA net. The performance amianecment is based activating smaller number of ncurons according to certain localized distribution. The study shows the ability of this scheme to learn an arbitrary function. The interaction of localizat on with other network parameters is discussed. | ||||
Statistics Article View: 67 PDF Download: 119 |
||||