A Self-Organizing Incremental Neural Network based on local distribution learning

详细信息    查看全文

• 作者：Youlu Xing^a ; ^b ; ^{youluxing@sina.com" class="auth_mail" title="E-mail the corresponding author} ; Xiaofeng Shi^a ; ^{cell000feng@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Furao Shen^a ; ^{frshen@nju.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; Ke Zhou^c ; ^{02417@uibe.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; Jinxi Zhao^a ; ^{jxzhao@nju.edu.cn" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Incremental learning ; Matrix learning ; Self-Organizing Incremental Neural Network (SOINN) ; Relaxation data representation
• 刊名：Neural Networks
• 出版年：2016
• 出版时间：December 2016
• 年：2016
• 卷：84
• 期：Complete
• 页码：143-160
• 全文大小：5668 K

文摘

In this paper, we propose an unsupervised incremental learning neural network based on local distribution learning, which is called Local Distribution Self-Organizing Incremental Neural Network (LD-SOINN). The LD-SOINN combines the advantages of incremental learning and matrix learning. It can automatically discover suitable nodes to fit the learning data in an incremental way without a priori knowledge such as the structure of the network. The nodes of the network store rich local information regarding the learning data. The adaptive vigilance parameter guarantees that LD-SOINN is able to add new nodes for new knowledge automatically and the number of nodes will not grow unlimitedly. While the learning process continues, nodes that are close to each other and have similar principal components are merged to obtain a concise local representation, which we call a relaxation data representation. A denoising process based on density is designed to reduce the influence of noise. Experiments show that the LD-SOINN performs well on both artificial and real-word data.