A Self-Organizing Incremental Neural Network based on local distribution learning
A Self-Organizing Incremental Neural Network based on local distribution learning
复制标题
DOI：
10.1016/j.neunet.2016.08.011
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Youlu Xing;Xiaofeng Shi;S. Furao;Ke Zhou;Jinxi Zhao
中科院分区：
文献类型：
--
作者：
Youlu Xing;Xiaofeng Shi;S. Furao;Ke Zhou;Jinxi Zhao
本文提出了一种基于局部分布学习的无监督增量学习神经网络，称为局部分布自组织增量神经网络（LD-SOINN）。LD-SOINN结合了增量学习和矩阵学习的优点。它可以自动发现合适的节点，以增量的方式来适应学习数据，而无需先验知识，如网络的结构。网络的节点存储关于学习数据的丰富的本地信息。自适应警戒参数保证了LD-SOINN能够自动添加新知识的新节点，并且节点数量不会无限增长。在学习过程继续的同时，相互接近且具有相似主成分的节点被合并以获得简洁的局部表示，我们称之为松弛数据表示。设计了一种基于密度的去噪过程，以降低噪声的影响。实验表明，LD-SOINN对人工和真实数据都有很好的识别效果。
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.