|
|
|
| ε-Insensitive Criterion and Structure Risk Based Radius-basis-function Neural-network Modeling |
| Sang Qing-bing① Deng Zhao-hong② Wang Shi-tong② Wu Xiao-jun① |
①(School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China)
②(School of Digital Media, Jiangnan Unversity, Wuxi 214122, China) |
|
|
|
|
Abstract An ε- insensitive criterion and structure risk based Radius-Basis-Function Neural-Network (RBF-NN) modeling method is proposed. By ε-introducing insensitive criterion and the item of structure risk, the RBF-NN learning is transformed into the linear regression and Quadratic Program (QP) optimization issue. Compared with the traditional least-square-criterion based RBF-NN training algorithms, the proposed method is much more robust to noise data and small size of datasets. Through the simulation experiments on the synthetic and real-word datasets, the above virtues are confirmed.
|
|
Received: 11 October 2011
|
|
|
|
Corresponding Authors:
Sang Qing-bing
E-mail: sangqb@163.com
|
|
|
|
|
|
|
2012, Vol. 34 
