基于GA的神经网络在手写数字识别中的应用研究-模式识别与智能系统专业论文.docxVIP

基于GA的神经网络在手写数字识别中的应用研究模式识剐与智能系统专韭 基于GA的神经网络在手写数字识别中的应用研究 模式识剐与智能系统专韭 研究生：蒋伟 指毒教筛： 古钟璧 手写数字识别(Handwritten Digits Recognition，简称HDR)是光学字符识 别技术(Optical Character Recognition，简称OCR)的一个分支，它在邮政编码 自动识别、银行、金融及模式识别理论研究等众多领域有麓广泛的应用前景。 人王享中经嬲终(Artificial Neural Network，简称ANN)的兴起源囊予人类对 爨身静模镑。1943年出现了神经元豹数学模型，随后出现豹学习算法逮一步摊 动了对神经网络静研究，面且逐渐遗从功能模拟为目标转囱基于知识处理的应 用研究。BP神经翮络由于其葬法简单而且有效焉在实舔中瘫用广泛。 遗传算法(Genetic Algorithm，简称GA)矩一种基予这尔文岛然避傀论耜鬣 德尔遗传变异理论的高效并行全局搜索方法，它能在援索过程中自劝获取和积 累有关搜索空间的知识，并自适应地控制搜索过程以求得最优解。 本文从神经网络和遗传算法基本理论及算法构成入手，将神经网络用于手 写数字识别中。针对BP神经嘲络易陷予局部最优解、依赖初始权值等缺点， 提出了用遗传算法取代BP神经网络中的BP学习算法。并结合实际的手写数据 库，对该算法帮BP算法进纾了比较。 试验结采表甥：基予遗传算法弱摊缎网络曩予手笔数字豹识别是可行蛉秘 有效的，该算法能够避免陷于精都最优解，不依赖于网络韧始权僮，也熊达到 较高的识别率。 关键词； 神经网络BP算法遗传算法手写数字识剐 Application Application of Genetic Algorithm Based Neural Network in Handwritten Digits Recognition Major：Patter RecognitionIntelligent System Graduate：Jiang，Wei Advisor：Gu，Zhongbi Handwritten digits recognition is one branch of optical character recognition (OCR)，which has broad potential application in fields of postal service，banking， finance and pattern recognition theory research． Artificial neural network originates from human’S imitation to self．The mathematical model of neural eell was presented in 1 943 and the following advance of learning algorithrn encouraged the research of neural network． Backpropagation(BP)learning algorithm is commonly used in practical use because of its simple and emciency． Genetic Algorithm(GA)is a kind of parallel and efficient search algorithm for global optimal solution，which is based on Darwin’S natulal evolution theory and Mendel’S genetic mutation theory．GA has the ability of automatic acquiring and storing knowledge of search space in the process of searching optimal solution and can adaptively control the search process to approach the optimal solution． In this thesis，the author based on the basic theory of neural network and genetic algorithm and applied genetic algorithm based neural network to haftdwritten digits recogniti