Research on the Hardware RBF Fuzzy Neural based on the FPGA

DOI

10.2991/isci-15.2015.168How to use a DOI?

Keywords

RBF Fuzzy Neural; FPGA; Excitation Function; Function Approximation

Abstract

To meet the real-time requirements of industrial field, the hardware FPGA RBF fuzzy neural network is designed and implemented based on the 250000 door Spartan-3E (XC3S250E) chip of Xilinx. First the structure and algorithm of RBF fuzzy neural network is introduced, and then a kind of improved hybrid excitation function approximation algorithm is put forward in order to overcome the difficulties in the hardware design of the neural network, and the hardware co-imitation and timing simulation is done on it. The experimental results demonstrates that, the method has better identification precision and speed, and it is a effective method of hardware implementation of RBF fuzzy neural network, and it lays the foundation for control and image processing based on hardware neural network.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bing Xu
AU  - Fei Guo
PY  - 2015/01
DA  - 2015/01
TI  - Research on the Hardware RBF Fuzzy Neural based on the FPGA
BT  - Proceedings of the 2015 International Symposium on Computers & Informatics
PB  - Atlantis Press
SP  - 1268
EP  - 1276
SN  - 2352-538X
UR  - https://doi.org/10.2991/isci-15.2015.168
DO  - 10.2991/isci-15.2015.168
ID  - Xu2015/01
ER  -