DocumentCode :
1789633
Title :
The implementation of feedforward network on field programmable gate array
Author :
Bin Deng ; Maohua Zhang ; Fei Su ; Jiang Wang ; Xile Wei ; Bonan Shan
Author_Institution :
Sch. of Electr. Eng. & Autom., Tianjin Univ., Tianjin, China
fYear :
2014
fDate :
14-16 Oct. 2014
Firstpage :
483
Lastpage :
487
Abstract :
Multilayer feedforward networks are related to functional groups of neurons where information is transmitted from one group to the next. It is a generic framework to characterize the properties of spiking activities in propagation. In this paper, we designed a novelty structure of feedforward network on FPGA to propagate the synchronous spiking activities. The experiment results demonstrate that the hardware implemented feedforward network can achieve the same synchronized states as the results of software simulation and show the high performance of FPGA implementation. The implementation of the feedforward network using one of the Altera Stratix III series FPGA boards is presented.
Keywords :
feedforward neural nets; field programmable gate arrays; Altera Stratix III series FPGA boards; field programmable gate array; hardware implemented feedforward network; multilayer feedforward networks; software simulation; synchronized states; synchronous spiking activities; Arrays; Biological system modeling; Computational modeling; Feedforward neural networks; Field programmable gate arrays; Neurons; Synchronization; Field programmable gate array (FPGA); feedforward network (FFN); leaky integrate and fire (LIF) neuron model; synapses model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2014 7th International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4799-5837-5
Type :
conf
DOI :
10.1109/BMEI.2014.7002823
Filename :
7002823
Link To Document :
بازگشت