《2943984503神经网络及卷积神经网络用于手写数字识别(ppt).ppt》由会员分享,可在线阅读,更多相关《2943984503神经网络及卷积神经网络用于手写数字识别(ppt).ppt(20页珍藏版)》请在三一办公上搜索。
1、A Hand-writing digit recognition Application base on Neural network and covolutional neural network,Colleague of Computer ScienceInner Mongolia UniversityHohhot,Inner Mongolia,P.R ChinaEmail:,NN digit recognition,1.Background2.Method neural network back-propagation3.Experiment training and testing s
2、amples neural network structure results,OCR(Optical Character Recognition)has become one of the important methods in gathering information and information transformation.Digit recognition has a promising feature in many fields in society,such as the car license plate recognition,postcode recognition
3、,the statistics of report forms and financial report forms.So the research on the Digit recognition is important.,background,neural network,Neural network is a machine learning method.,method,Back Propagation,Back propagation(BP)is a neural network learning algorithm.,method,Environment,Hardware:CPU
4、:Intel core i7 3630QM,2.4GHZ Memory:8G ByteSoftware:OS:windows 7(64)IDE:vs2010(C+),Experiment,Experiment-Training and testing Samples,Training and testing samples are fromMNIST,http:/pic is a 28*28 dot matrixThere are 10 pics in a sample,and there are 891 samples,Experiment,Neural network design,Our
5、 neural network has 3 layers:,Experiment,neural network design,BP neural network,Experiment,results,Training samples:Testing samples:,Experiment,2023/2/28,卷积神经网络,基于人工神经网络在人工神经网络前,用滤波器进行特征抽取使用卷积核作为特征抽取器自动训练特征抽取器(即卷积核,即阈值参数),2023/2/28,卷积,卷积其实是一个图像处理核卷积用于增强图像的某种特征,2023/2/28,卷积的例子,2023/2/28,子采样,降低图像分辨率减少训练维数增强网络对大小变化的适用性,2023/2/28,一般卷积神经网络的结构,2023/2/28,我的卷积神经网络结构,2023/2/28,实验效果,2023/2/28,训练时间次数及准确率,2023/2/28,问题,1 准确率太低2 准确率抖动厉害3 单线程,训练速度太慢,Thank you for listening!,