Efficient Sigmoid Function for Neural Networks Based FPGA Design
Efficient design of sigmoid function for neural networks based FPGA is presented. Employing the hybrid CORDIC algorithm, the sigmoid function is described with VHDL in register transfer level. In order to enhance the efficiency and accuracy of implementation on Altera’s FPGA, the technology of pipeline and look-up table have been utilized. Through comparing the results obtained by the post-simulation of EDA tools with the results directly accounted by Matlab, it can be concluded that the designed model works accurately and efficiently.
KeywordsSigmoid Function Register Transfer Level CORDIC Algorithm CORDIC Iteration Spring Joint Computer
Unable to display preview. Download preview PDF.
- 2.Martin, T.H., Howard, B., Demuth, M.B.: Neural Networks Design. China Machine Press (2002)Google Scholar
- 3.Ouali, J., Saucier, G.: Fast Generation of Neuron-ASICs. In: Proc. Int. Neural Networks Conf., pp. 563–567 (1990)Google Scholar
- 4.Murtagh, P., Tsoi, A.C.: Implementation Issues of Sigmoid Function and Its Derivative for VLSI Digital Neural Networks. In: IEE Proceedings on Computers and Digital Techniques, pp. 207–213 (1992)Google Scholar
- 5.Walther, J.: A Unified Algorithm for Elementary Functions. In: Spring Joint Computer Conf. Proc., pp. 379–385 (1971)Google Scholar
- 7.Xia, F.: Efficient Arithmetic Functional Modules for FPGA-based VLSI Design. Master Dissertation, Nan Yang Technological University, Singapore (2005)Google Scholar