Implementation of High Speed Tangent Sigmoid Transfer Function Approximations for Artificial Neural Network Applications on FPGA
| Autor: | Ismail Koyuncu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
lcsh:Computer engineering. Computer hardware
General Computer Science Computer science Computer Science::Neural and Evolutionary Computation lcsh:TK7885-7895 02 engineering and technology approximation methods Topology Transfer function Computer Science::Hardware Architecture 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Hardware_ARITHMETICANDLOGICSTRUCTURES Field-programmable gate array Sigmoid transfer function field programmable gate arrays Artificial neural network 020208 electrical & electronic engineering Tangent Sigmoid function Exponential function Nonlinear system real-time systems transfer functions 020201 artificial intelligence & image processing lcsh:Electrical engineering. Electronics. Nuclear engineering artificial neural networks lcsh:TK1-9971 |
| Zdroj: | Advances in Electrical and Computer Engineering, Vol 18, Iss 3, Pp 79-86 (2018) |
| ISSN: | 1844-7600 1582-7445 |
| Popis: | Tangent Sigmoid (TanSig) Transfer Function (TSTF) is one of the nonlinear functions used in Artificial Neural Networks (ANNs). As TSTF includes exponential function operations, hardware-based implementation of this function is difficult. Thus, various methods have been proposed in the literature for the hardware implementation of TSTF. In this study, four different TSTF approaches on FPGA have been implemented using 32-bit IEEE 754–1985 floating point number standard, and their performance analyses and FPGA chip statistics are presented. The Van der Pol system ANN application was carried out using four different FPGA-based TSTF units presented. The Multilayer feed-forward neural network structure was used in the study. The FPGA chip statistics and sensitivity analyses were carried out by applying each TSTF structure to the exemplary ANN. The maximum operating frequency of ANNs designed on FPGA using the four different TSTF units varied between 184–362 MHz. The CORDIC-LUT-based ANN on FPGA was able to calculate 1 billion results in 3.284 s. According to the Van der Pol system ANN application carried out on FPGA, the CORDIC-LUT-based approach most closely reflected the reference ANN results. This study has a reference and key research for real-time artificial neural network applications used of tangent sigmoid one of the nonlinear transfer functions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|