Efficient digital implementation of the sigmoid function for reprogrammable logic
IEE Proceedings - Computers and Digital Techniques2003Vol. 150(6), pp. 403–403
Citations Over TimeTop 18% of 2003 papers
Abstract
Special attention must be paid to an efficient approximation of the sigmoid function in implementing FPGA-based reprogrammable hardware-based artificial neural networks. Four previously published piecewise linear and one piecewise second-order approximation of the sigmoid function are compared with SIG-sigmoid, a purely combinational approximation. The approximations are compared in terms of speed, required area resources and accuracy measured by average and maximum error. It is concluded that the best performance is achieved by SIG-sigmoid.
Related Papers
- → A non-linear approximation of the sigmoid function based on FPGA(2012)16 cited
- → A Neural Network Approximation Based on a Parametric Sigmoidal Function(2019)11 cited
- → Neuro-Fuzzy Function Approximations Using Feedforward Networks - An Application of Sigmoidal Signal(2010)4 cited
- → Piecewise Constant Signal Estimation by the Recording of Signal Measurements in a Linear Scheme(2021)1 cited
- Function Approximations using FF Networks(2013)