姚明臣,张超,吴微.分类问题的在线顺序双并联快速学习机[J].数学研究及应用,2016,36(5):621~630
分类问题的在线顺序双并联快速学习机
Online Sequential Double Parallel Extreme Learning Machine for Classifications
投稿时间:2015-07-24  最后修改时间:2015-11-09
DOI:10.3770/j.issn:2095-2651.2016.05.012
中文关键词:  双并联前馈神经网络  感知机  快速学习机  分类问题
英文关键词:double parallel forward neural network  perception  extreme learning machine  classification problems
基金项目:国家自然科学基金(Grant Nos.11401076; 61473328; 11171367; 61473059).
作者单位
姚明臣 大连理工大学数学科学学院, 辽宁 大连 116024 
张超 大连理工大学数学科学学院, 辽宁 大连 116024 
吴微 大连理工大学数学科学学院, 辽宁 大连 116024 
摘要点击次数: 597
全文下载次数: 900
中文摘要:
      双并联前馈神经网络模型是单层感知机和单隐层前馈神经网络的混合结构,本文构造了一种双并联快速学习机算法,与其他类似算法比较,提出的算法能利用较少的隐层单元及更少的待定参数,获得近似的学习性能.数值实验表明,对很多实际分类问题,提出的算法具备更佳的泛化能力,因而可以作为快速学习机算法的有益补充.
英文摘要:
      Double parallel forward neural network (DPFNN) model is a mixture structure of single-layer perception and single-hidden-layer forward neural network (SLFN). In this paper, by making use of the idea of online sequential extreme learning machine (OS-ELM) on DPFNN, we derive the online sequential double parallel extreme learning machine algorithm (OS-DPELM). Compared to other similar algorithms, our algorithms can achieve approximate learning performance with fewer numbers of hidden units, as well as the parameters to be determined. The experimental results show that the proposed algorithm has good generalization performance for real world classification problems, and thus can be a necessary and beneficial complement to OS-ELM.
查看全文  查看/发表评论  下载PDF阅读器