文章基本信息

标题：Mutual Information-Based Modified Randomized Weights Neural Networks
本地全文：下载
作者：Jian Tang ; Zhiwei Wu ; Meiying Jia 等
期刊名称：Journal of Computer and Communications
印刷版ISSN：2327-5219
电子版ISSN：2327-5227
出版年度：2015
卷号：03
期号：11
页码：191-197
DOI：10.4236/jcc.2015.311030
语种：English
出版社：Scientific Research Publishing
摘要：Randomized weights neural networks have fast learning speed and good generalization performance with one single hidden layer structure. Input weighs of the hidden layer are produced randomly. By employing certain activation function, outputs of the hidden layer are calculated with some randomization. Output weights are computed using pseudo inverse. Mutual information can be used to measure mutual dependence of two variables quantitatively based on the probability theory. In this paper, these hidden layer’s outputs that relate to prediction variable closely are selected with the simple mutual information based feature selection method. These hidden nodes with high mutual information values are maintained as a new hidden layer. Thus, the size of the hidden layer is reduced. The new hidden layer’s output weights are learned with the pseudo inverse method. The proposed method is compared with the original randomized algorithms using concrete compressive strength benchmark dataset.
关键词：Randomized Weights Neural Networks;Mutual Information;Feature Selection