| 基于极速学习的粗糙RBF神经网络 |
| |
| 引用本文： | 马刚,丁世飞,史忠植. 基于极速学习的粗糙RBF神经网络[J]. 微电子学与计算机, 2012, 29(8): 9-14 |
| |
| 作者姓名： | 马刚 丁世飞 史忠植 |
| |
| 作者单位： | 1. 中国矿业大学计算机科学与技术学院,江苏徐州221008／中国科学院计算技术研究所,北京100190
2. 中国科学院计算技术研究所,北京,100190 |
| |
| 基金项目： | 国家自然科学基金，中国科学院智能信息处理重点实验室开放基金 |
| |
| 摘 要： | 提出了一种用于训练粗糙RBF神经网络(rough RBF neural networks,R-RBF)的极速学习机(extreme learning machine,ELM)方法,通过引入矩阵的Moore-Penrose逆,将传统的迭代学习方法转换为一种求线性方程的极小范数最小二乘解的方法.实验证明,在训练精度、训练时间上都能够达到非常优越的性能,其泛化精度能够提升50%以上.
|
| 关 键 词： | ELM R-RBF Moore-Penrose 极小范数最小二乘解 |
Rough RBF Neural Network Based on Extreme Learning |
| |
| MA Gang,DING Shi-fei,SHI Zhong-zhi. Rough RBF Neural Network Based on Extreme Learning[J]. Microelectronics & Computer, 2012, 29(8): 9-14 |
| |
| Authors: | MA Gang DING Shi-fei SHI Zhong-zhi |
| |
| Affiliation: | 1 School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221008,China; 2 Institute of Computing Technology,Chinese Academy of Science,Beijing 100190,China) |
| |
| Abstract: | The paper proposes a method of training rough RBF neural networks(R-RBF) using the extreme learning machine(ELM),which converts the traditional iterative training method to solve norm least-squares solution of general linear system by introducing Moore-Penrose inverse.Experiments show that it can reach a very superior performance in both time and accuracy when ELM trains the Rough RBF Neural Networks,which can improve the generalization accuracy more than 50% compared with the traditional thinking of adjusting parameters iteratively. |
| |
| Keywords: | ELM R-RBF~ Moore-Penrose norm least-squares solution |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
