|
|
|
| Rough Neural Network Based on Variable Precision Rough Set |
| Zhang Dong-bo①②; Wang Yao-nan②;Huang Hui-xian① |
| ①Institute of Information Engineering, Xiangtan University, Xiangtan 411105, China; ②College of Electrical and Information Engineering, Hunan University, Changsha 410082, China |
|
|
|
|
Abstract The design of the rough neural network based on variable precision rough set model is studied. The condition of β -approximation reduction is generalized and the criteria for selecting a β -approximation reduction are introduced. In the experiment of the Brodatz texture image classification, the performance of conventional RNN(Rough Neural Network) and VPRNN(Variable Precision Rough set Neural Network) is compared. The results indicate that VPRNN not only has more simplify structure and less training time, but also, has better approximation decision-making ability and generalization ability than RNN.
|
|
Received: 19 January 2007
|
|
|
|
|
|
|
|
|
2008, Vol. 30 
