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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Sheng-He SUN, Xiao-Dan MEI, Zhao-Li ZHANG, "A Novel Rough Neural Network and Its Training Algorithm" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 2, pp. 426-431, February 2002, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_2_426/_p
Copy
@ARTICLE{e85-d_2_426,
author={Sheng-He SUN, Xiao-Dan MEI, Zhao-Li ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Rough Neural Network and Its Training Algorithm},
year={2002},
volume={E85-D},
number={2},
pages={426-431},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - A Novel Rough Neural Network and Its Training Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 426
EP - 431
AU - Sheng-He SUN
AU - Xiao-Dan MEI
AU - Zhao-Li ZHANG
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2002
AB - 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.
ER -