基于高斯神经元的自组织映射网络研究  

Research on Self-organizing Map Network Based on Gaussian Neuron

作　　者：刘达 陈松灿[1] LIU Da;CHEN Songcan(College of Computer Science and Technology,Nanjing University of Aeronautics&Astronautics,Nanjing 211106,China)

机构地区：[1]南京航空航天大学计算机科学与技术学院,南京211106

出　　处：《数据采集与处理》2023年第1期85-92,共8页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61732006)。

摘　　要：自组织映射网络(Self-organizing map network,SOM)是一种经典的无监督学习方法,具有自组织和联机学习功能。由于其简明与实用等特点,不断涌现出SOM变体以适应各类问题。然而,这些工作基本都采纳了确定性神经元建立网络,忽略了数据本身隐含的不确定性信息,导致这些模型的结果缺乏由置信度反映的可解释性,意味着SOM神经元的不确定性刻画能力不足。本文提出了一种高斯神经元SOM网络(Ganssian neuron som network,GNSOM),其神经元节点不再是确定性的,而是建模为高斯分布的高斯神经元,为SOM配备了不确定性功能用于表述数据的不确定性。在实现时,将输入数据同样高斯化,并用Jensen-Shannon(JS)散度代替SOM学习中的欧氏距离作为GNSOM学习中的相似性匹配度量,由此获得了不确定性表示。实验结果表明,GNSOM具有更好的训练效果,并能通过神经元节点的协方差矩阵反映数据的不确定性。由于这种对神经元的高斯化独立于SOM本身,因此能拓展应用于其他神经元模型。Self-organizing map network(SOM)is a classic unsupervised learning method with selforganizing and online learning functions.Due to its simplicity and practicality,SOM variants have been emerging to adapt to various problems.However,these work basically adopts deterministic neurons to build networks,ignoring the uncertainty information implicit in the data itself.This results in a lack of interpretability reflected by confidence in the results of these models,implying that the uncertainty characterization ability of SOM neurons is insufficient.This article proposes a new variant of SOM,called the Gaussian neuron SOM network(GNSOM).Its neuron nodes are no longer deterministic,but modeled as Gaussian neurons with Gaussian distribution.Thus,SOM is equipped with an uncertainty function to express the uncertainty of the data.In implementation,the input data are also Gaussianized,and the Jensen-Shannon(JS)divergence is used to replace the Euclidean distance as the similarity matching metric in GNSOM learning,thereby obtaining the uncertainty representation.The experimental results show that GNSOM has a better training effect,and can reflect the uncertainty of the data through the covariance matrix of the neuron node.Since this Gaussization of neurons is independent of SOM itself,it can be extended to other neuron models.

关 键 词：无监督学习 自组织映射网络 数据不确定性 高斯神经元自组织映射 JS散度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]