Digital Recognition Based on Neural Network and FPGA Implementation

被引：3

作者：

Zhang, Chaoyue ^{[1
,3
]}

Wang, Yu ^{[1
,3
]}

Guo, Jinxu ^{[1
,3
]}

Zhang, Hao ^{[2
]}

机构：

[1] Wuhan Univ Technol, Coll Informat Engn, Wuhan, Hubei, Peoples R China

[2] Wuhan Univ Technol, Coll Management, Wuhan, Hubei, Peoples R China

[3] Wuhan Univ Technol, Minist Educ, Key Lab Fiber Opt Sensing Technol & Informat Proc, Wuhan, Hubei, Peoples R China

来源：

2017 NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS (IHMSC 2017), VOL 1 | 2017年

关键词：

neural network; Digital recognition; FPGA; Forward propagation;

D O I：

10.1109/IHMSC.2017.71

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In recent years, neural network is widely used in many fields such as pattern recognition, signal processing and so on. Digital recognition is an important branch in the field of pattern recognition. The main content of this paper is the realization of digital recognition of BP neural network on the hardware. Because in the actual scene, many times in the system design, we need to consider the reality. Compared with the traditional software implementation, FPGA has the characteristics of parallelism, which can greatly improve the processing speed and meet the application requirements. In this paper, the off-line training method is used to store the off-line training data into RAM, and the forward propagation process of BP neural network is realized on FPGA.

引用

页码：280 / 283

页数：4

共 6 条

[1] HARDWARE IMPLEMENTATION OF AN ARTIFICIAL NEURAL-NETWORK USING FIELD-PROGRAMMABLE GATE ARRAYS (FPGAS) [J].

BOTROS, NM ;

ABDULAZIZ, M .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1994, 41 (06) :665-667

[2]

Ferreira P, 2004, LECT NOTES COMPUT SC, V3203, P1084

[3]

Gao CJ, 2003, IEEE IJCNN, P995

[4]

Wang Hu, 2007, Computer Engineering and Applications, V43, P86

[5]

Wang QR, 2003, IEEE SYS MAN CYBERN, P762

[6]

Zhao Zhen-hua, 2009, MICROCONTROLLERS EMB, P12

← 1 →