Study on Deep Structure of Extreme Learning Machine (DS-ELM) for Datasets with Noise
Study on Deep Structure of Extreme Learning Machine (DS-ELM) for Datasets with Noise
复制标题
DOI：
10.4028/www.scientific.net/amr.989-994.3679
复制
发表时间：
2014-07
期刊：
影响因子：
--
通讯作者：
M. Ma;Bo He
中科院分区：
文献类型：
--
作者：
M. Ma;Bo He
极限学习机（Extreme learning machine， ELM）是一种相对较新的针对单隐层前馈神经网络（SLFNs）的机器学习算法，具有结构简单、训练速度快等优点。为了提高ELM处理噪声数据集的有效性，本文提出了一种深度ELM结构，简称DS-ELM。DS-ELM包含三级网络（实际包含三个网络）：第一级网络由自关联神经网络（AANN）训练，目的是滤除噪声，必要时进行降维；第二层网络是另一个AANN网络，目的是固定ELM的输入权值和偏置；最后一层网络是ELM。在4个噪声数据集上进行了实验，验证了新提出的DS-ELM算法。结果表明，在处理噪声数据时，DS-ELM比ELM具有更高的性能。
Extreme learning machine (ELM), a relatively novel machine learning algorithm for single hidden layer feed-forward neural networks (SLFNs), has been shown competitive performance in simple structure and superior training speed. To improve the effectiveness of ELM for dealing with noisy datasets, a deep structure of ELM, short for DS-ELM, is proposed in this paper. DS-ELM contains three level networks (actually contains three nets ): the first level network is trained by auto-associative neural network (AANN) aim to filter out noise as well as reduce dimension when necessary; the second level network is another AANN net aim to fix the input weights and bias of ELM; and the last level network is ELM. Experiments on four noisy datasets are carried out to examine the new proposed DS-ELM algorithm. And the results show that DS-ELM has higher performance than ELM when dealing with noisy data.