基于LVQ神经网络的手写数字识别研究与实现  

Research and Discoveries in Hand-written Number Recognition Based on LVQ Nerve Net

作　　者：叶晓波[1] 秦海菲 吕永林 YE Xiaobo;QIN Haifei;LV Yonglin(Institute of Network&Information Systems,Chuxiong Normal University,Chuxiong,Yunnan Province,675000;School of Information Sciences&Technology,Chuxiong Normal University,Chuxiong,Yunnan Province,675000;School of Economics&Management,Chuxiong Normal University,Chuxiong,Yunnan Province,675000)

机构地区：[1]楚雄师范学院网络与信息系统研究所,云南楚雄675000 [2]楚雄师范学院信息科学与技术学院,云南楚雄675000 [3]楚雄师范学院经济与管理学院,云南楚雄675000

出　　处：《楚雄师范学院学报》2018年第3期70-78,共9页Journal of Chuxiong Normal University

摘　　要：提出基于LVQ神经网络的手写数字识别方法并进行实验研究。介绍了LVQ神经网络的基本原理,分析了MNIST手写数字数据库的数据结构,阐述了LVQ神经网络的参数选择方法,介绍了PCA降维方法,详细论述了基于LVQ神经网络的手写数字识别实验的整个过程,分析了实验结果。This paper proposes a method of hand-written number recognition based on LVQ nerve net and presents the experiment on said method.After describing the basic principle of the LVQ nerve net,the paper proceeds to analyze the data structure of the MNIST hand-written number database,describe the parameter selection method of the LVQ nerve net as well as the method for PCA dimensionality reduction and demonstrate,in details,the whole experiment process of hand-written number recognition based on the LVQ nerve net before finally analyzing results of said experiment.

关 键 词：LVQ神经网络 手写数字 MNIST PCA降维 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]