Implementation of a neuro-fuzzy network with on-chip learning and its applications

被引：8

作者：

Lin, Cheng-Jian ^{[1
]}

Lee, Chi-Yung ^{[2
]}

机构：

[1] Natl Chin Yi Univ Technol, Dept Comp Sci & Informat Engn, Taichung 411, Taiwan

[2] Nankai Univ Technol, Dept Comp Sci & Informat Engn, Nantou 542, Taiwan

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2011年 / 38卷 / 01期

关键词：

Neural fuzzy network (NFN); Field programmable gate array (FPGA); Backpropagation (BP) method; Simultaneous perturbation; Gaussian function; FIXED-POINT; SYSTEMS;

D O I：

10.1016/j.eswa.2010.07.019

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The implementation of adaptive neural fuzzy networks (NFNs) using field programmable gate arrays (FPGA) is proposed in this study. Hardware implementation of NFNs with learning ability is very difficult. The backpropagation (BP) method in the learning algorithm is widely used in NFNs, making it difficult to implement NFNs in hardware because calculating the backpropagation error of all parameters in a system is very complex. However, we use the simultaneous perturbation method as a learning scheme for the NFN hardware implementation. In order to reduce the chip area, we utilize the traditional non-linear activation function to implement the Gaussian function. We can confirm the reasonableness of NFN performance through some examples. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.

引用

页码：673 / 681

页数：9

共 21 条

[11] Maeda Y., 1993, Electronics and Communications in Japan, Part 3 (Fundamental Electronic Science), V76, P17, DOI 10.1002/ecjc.4430760403
[12] Learning rules for neuro-controller via simultaneous perturbation
Maeda, Y
DeFigueiredo, RJP
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (05): : 1119 - 1130
[13] A LEARNING RULE OF NEURAL NETWORKS VIA SIMULTANEOUS PERTURBATION AND ITS HARDWARE IMPLEMENTATION
MAEDA, Y
HIRANO, H
KANATA, Y
[J]. NEURAL NETWORKS, 1995, 8 (02) : 251 - 259
[14] Maeda Y., 1993, Transactions of the Institute of Electrical Engineers of Japan, Part C, V113-C, P402
[15] Mohd-Yasin F, 2004, 16TH INTERNATIONAL CONFERENCE ON MICROELECTRONICS, PROCEEDINGS, P458
[16] Subsethood-product fuzzy neural inference system (SuPFuNIS)
Paul, S
Kumar, S
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (03): : 578 - 599
[17] Sheu B.J., 1995, Neural Information Processing and VLSI, P277
[18] Spall J. C., 1987, Proceedings of the 1987 American Control Conference, P1161
[19] FUZZY IDENTIFICATION OF SYSTEMS AND ITS APPLICATIONS TO MODELING AND CONTROL
TAKAGI, T
SUGENO, M
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1985, 15 (01): : 116 - 132
[20] Efficient digital implementation of the sigmoid function for reprogrammable logic
Tommiska, MT
[J]. IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES, 2003, 150 (06): : 403 - 411

← 1 2 3 →