Two-stage extreme learning machine for high-dimensional data

Two-stage extreme learning machine for high-dimensional data
复制标题

高维数据的两阶段极限学习机

DOI:
10.1007/s13042-014-0292-7
复制
发表时间:
2014-08
影响因子:
5.6
通讯作者:
Zhang, Guopeng
Zhang, Guopeng
中科院分区:
计算机科学3区
文献类型:
--
作者:
Huang, Yihua;Meng, Lei;Gong, Siyuan;Zhang, Guopeng

文献摘要

参考文献

被引文献

相似文献

极限学习机(ELM)通过在隐含层应用随机计算节点来解决快速有监督学习问题。与支持向量机类似,ELM不能有效地处理高维数据。当处理高维数据时,其泛化性能往往会变差。为了有效利用高维数据,建立了两阶段极端学习机模型。在第一阶段,我们将ELM引入到谱回归算法中,实现对高维数据的降维,并计算输出权重。在第二阶段,基于低维数据和得到的输出权重计算标准ELM模型的决策函数。这是因为两个阶段都是基于榆树的。因此,第二级中的输出权重可以被第一级中的输出权重近似地替换。因此,该方法能够以较快的学习速度适用于高维数据。实验结果表明,与ELM相比,提出的两阶段ELM方案具有更好的可扩展性,在更快的学习速度下获得了优异的泛化性能。
Extreme learning machine (ELM) has been proposed for solving fast supervised learning problems by applying random computational nodes in the hidden layer. Similar to support vector machine, ELM cannot handle high-dimensional data effectively. Its generalization performance tends to become bad when it deals with high-dimensional data. In order to exploit high-dimensional data effectively, a two-stage extreme learning machine model is established. In the first stage, we incorporate ELM into the spectral regression algorithm to implement dimensionality reduction of high-dimensional data and compute the output weights. In the second stage, the decision function of standard ELM model is computed based on the low-dimensional data and the obtained output weights. This is due to the fact that two stages are all based on ELM. Thus, output weights in the second stage can be approximately replaced by those in the first stage. Consequently, the proposed method can be applicable to high-dimensional data at a fast learning speed. Experimental results show that the proposed two-stage ELM scheme tends to have better scalability and achieves outstanding generalization performance at a faster learning speed than ELM.
DOI: 10.1007/bfb0015522
发表时间: 1996-04
期刊: --
影响因子: --
作者:
P. Belhumeur;J. Hespanha;D. Kriegman
通讯作者: P. Belhumeur;J. Hespanha;D. Kriegman
DOI: 10.1016/j.patcog.2011.03.013
发表时间: 2011-10-01
影响因子: 8
作者:
Mohammed, A. A.;Minhas, R.;Sid-Ahmed, M. A.
通讯作者: Sid-Ahmed, M. A.
DOI: --
发表时间: 2001
期刊: --
影响因子: --
作者:
P. Belhumeur;D. Kriegman
通讯作者: P. Belhumeur;D. Kriegman
DOI: --
发表时间: 2010
期刊: --
影响因子: --
作者:
Benoît Frénay;M. Verleysen
通讯作者: Benoît Frénay;M. Verleysen
DOI: 10.1109/tnn.2009.2036259
发表时间: 2010-01-01
影响因子: --
作者:
Miche, Yoan;Sorjamaa, Antti;Lendasse, Amaury
通讯作者: Lendasse, Amaury