A novel rough neural network and its training algorithm

被引：0

作者：

Sun, Sheng-He ^{[1
]}

Mei, Xiao-Dan ^{[1
]}

Zhang, Zhao-Li ^{[1
]}

机构：

[1] Dept. of Automatic Test and Ctrl., Harbin Institute of Technology, Harbin 150001, China

来源：

IEICE Transactions on Information and Systems | 2002年 / E85-D卷 / 02期

关键词：

Approximation theory - Backpropagation - Data reduction - Genetic algorithms - Iterative methods - Normal distribution - Transfer functions - Two dimensional;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

A novel rough neural network (RNN) structure and its application are proposed in this paper. We principally introduce its architecture and training algorithms: the genetic training algorithm (GA) and the tabu search training algorithm (TSA). We first compare RNN with the conventional NN trained by the BP algorithm in two-dimensional data classification. Then we compare RNN with NN by the same training algorithm (TSA) in functional approximation. Experiment results show that the proposed RNN is more effective than NN, not only in computation time but also in performance.

引用

下载

页码：426 / 431

共 50 条

[41] Research on Fusion Algorithm with BP Neural Network and Rough Set
Li Wei
He Peng-ju
Zhang Peng
Chen Ming
Jiang Li-jun
2011 6TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 2011, : 118 - 123
[42] A novel hybrid methodology combining back propagation neural network with rough set and its application
Deng, W.
Chen, R.
Liu, Y. Q.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART F-JOURNAL OF RAIL AND RAPID TRANSIT, 2011, 225 (F3) : 259 - 265
[43] A novel algorithm of image enhancement based on Pulse Coupled Neural Network time matrix and Rough Set
Ma, Yide
Lin, Dongmei
Zhang, Beidou
Xia, Chunshui
FOURTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, VOL 3, PROCEEDINGS, 2007, : 86 - 90
[44] A novel training algorithm for RBF neural network using a hybrid fuzzy clustering approach
Niros, Antonios D.
Tsekouras, George E.
FUZZY SETS AND SYSTEMS, 2012, 193 : 62 - 84
[45] A Novel Modification on the Levenberg-Marquardt Algorithm for Avoiding Overfitting in Neural Network Training
Iplikci, Serdar
Bilgi, Batuhan
Menemen, Ali
Bahtiyar, Bedri
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: DEEP LEARNING, PT II, 2019, 11728 : 201 - 207
[46] A Novel Hybrid Evolutionary Algorithm Based on PSO and AFSA for Feedforward Neural Network Training
Chen, Xuejun
Wang, Jianzhou
Sun, Donghuai
Liang, Jinzhao
2008 4TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, NETWORKING AND MOBILE COMPUTING, VOLS 1-31, 2008, : 10833 - +
[47] A novel method to stop neural network training
Iyer, MS
Rhinehart, RR
PROCEEDINGS OF THE 2000 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2000, : 929 - 933
[48] Fuzzy Rough Neural Network and Its Application to Feature Selection
Zhao, Junyang
Zhang, Zhili
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS, 2011, 13 (04) : 270 - 275
[49] Feedback procedure neural network and its training
Liang, JZ
Zhao, MS
2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, 2002, : 101 - 106
[50] A Rough-fuzzy RBF neural network based on PSO algorithm
Zhao, Jing
Advanced Materials Research, 2013, 710 : 617 - 622

← 1 2 3 4 5 →