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

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.