关于增量极限学习机的逼近阶估计
Journal of Northwest University(Natural Science Edition)（2015）
Abstract
与以往探究增量极限学习机的全局逼近能力有所不同,文中给出了该算法定量的收敛性分析.源于纯贪婪算法估计逼近阶的思想,文中运用数列构造与不等式缩放等方法估计增量极限学习机的逼近阶,最终用定理证明了它对于连续目标函数f的逼近阶为o(n-1/6).这就对增量极限学习机的快速收敛性能给出了清晰解释.
MoreKey words
Incremental extreme learning machine,greedy algorithm,dictionary,approximation rate
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined