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.
El-Serafi, K., & Moustafa, K. (2020). A Radial Base Localized Distribution for Deterministic Function Approximation Neural Networks.. MEJ- Mansoura Engineering Journal, 23(3), 1-9. doi: 10.21608/bfemu.2021.149971
MLA
K. A. El-Serafi; K. Z. Moustafa. "A Radial Base Localized Distribution for Deterministic Function Approximation Neural Networks.". MEJ- Mansoura Engineering Journal, 23, 3, 2020, 1-9. doi: 10.21608/bfemu.2021.149971
HARVARD
El-Serafi, K., Moustafa, K. (2020). 'A Radial Base Localized Distribution for Deterministic Function Approximation Neural Networks.', MEJ- Mansoura Engineering Journal, 23(3), pp. 1-9. doi: 10.21608/bfemu.2021.149971
VANCOUVER
El-Serafi, K., Moustafa, K. A Radial Base Localized Distribution for Deterministic Function Approximation Neural Networks.. MEJ- Mansoura Engineering Journal, 2020; 23(3): 1-9. doi: 10.21608/bfemu.2021.149971
)
View on SCiNiTO