arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.06975cs.LGcs.AIstat.ML
收藏

带有本地连接的极限学习机

Extreme Learning Machine with Local Connections

Dalian University of Technology(大连理工大学)

Feng Li, Sibo Yang, Huanhuan Huang, Wei Wu

摘要:

研究了极限学习机(ELM)输入隐权值的稀疏化问题。对于普通的前向神经网络,稀疏化通常是通过在网络的学习过程中引入某种正则化技术来实现的。但这种策略不能应用于ELM,因为ELM的输入隐藏权重应该是随机选择的,而不是学习的。为此,我们提出了一种改进的ELM,称为ELM-LC(ELM与本地连接),这是专为稀疏的输入隐藏权重如下:隐节点和输入节点分别分为几个相应的组,输入节点组是完全连接到其对应的隐节点组,但不连接到任何其他的隐节点组。与通常的ELM一样,隐输入权重随机给定,隐输出权重通过最小二乘学习获得。在一些基准问题的数值模拟中,新的ELM-CL表现优于传统的ELM。

英文摘要:

This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into the learning process of the network. But this strategy can not be applied for ELM, since the input-hidden weights of ELM are supposed to be randomly chosen rather than to be learned. To this end, we propose a modified ELM, called ELM-LC (ELM with local connections), which is designed for the sparsification of the input-hidden weights as follows: The hidden nodes and the input nodes are divided respectively into several corresponding groups, and an input node group is fully connected with its corresponding hidden node group, but is not connected with any other hidden node group. As in the usual ELM, the hidden-input weights are randomly given, and the hidden-output weights are obtained through a least square learning. In the numerical simulations on some benchmark problems, the new ELM-CL behaves better than the traditional ELM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑