|
|||||
|
|
| 基于灵敏度分析法的ELM剪枝算法 | |
| 引用本文： | 李凡军 韩红桂 乔俊飞. 基于灵敏度分析法的ELM剪枝算法[J]. 控制与决策, 2014, 29(6): 1003-1008 |
| 作者姓名： | 李凡军 韩红桂 乔俊飞 |
| 作者单位： | 北京工业大学电子信息与控制工程学院;济南大学数学科学学院 |
| 基金项目： | 国家自然科学基金项目(61034008,61203099,61225016);北京市自然科学基金项目(4122006);教育部博士点新教师基金项目(20121103120020) |
| 摘 要： | 针对极端学习机(ELM)网络结构设计问题,提出基于灵敏度分析法的ELM剪枝算法.利用隐含层节点输出和相对应的输出层权值向量,定义学习残差对于隐含层节点的灵敏度和网络规模适应度,根据灵敏度大小判断隐含层节点的重要性,利用网络规模适应度确定隐含层节点个数,删除重要性较低的节点.仿真结果表明,所提出的算法能够较为准确地确定与学习样本相匹配的网络规模,解决了ELM网络结构设计问题. |
| 关 键 词： | 前馈神经网络 极端学习机 灵敏度分析 剪枝算法 |
| 收稿时间： | 2013-03-22 |
| 修稿时间： | 2013-06-22 |
Pruning algorithm for extreme learning machine based on sensitivity analysis |
|
| LI Fan-jun HAN Hong-gui QIAO Jun-fei. Pruning algorithm for extreme learning machine based on sensitivity analysis[J]. Control and Decision, 2014, 29(6): 1003-1008 | |
| Authors: | LI Fan-jun HAN Hong-gui QIAO Jun-fei |
| Affiliation: | LI Fan-jun;HAN Hong-gui;QIAO Jun-fei;College of Electronic Information and Control Engineering,Beijing University of Technology;School of Mathematical Science,Ji’nan University; |
| Abstract: | In order to design the structure of extreme learning machine(ELM), a pruning algorithm is proposed by using the sensitivity analysis method. The residual error’s sensitivities to the hidden nodes are defined by their outputs and weight vectors connecting to the output layer. The model scale adaptability is calculated and the hidden nodes are sorted by using the defined sensitivities. Then, the number of requisite hidden nodes is estimated by the model scale adaptability. The redundant nodes with smaller sensitivities are removed from the existent network. The simulation results show that the proposed approach can construct the compact structure for ELM effectively. |
| Keywords: | feedforward neural networks|extreme learning machine|sensitivity analysis|pruning algorithm |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《控制与决策》浏览原始摘要信息 | |
| 点击此处可从《控制与决策》下载全文 | |