神经网络及其卷积神经网络用于手写数字识别.pptVIP

Colleague of Computer Science Inner Mongolia University Hohhot , Inner Mongolia , P.R China Email: huangzhiqiang@ 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） 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 卷积的例子 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 一般卷积神经网络的结构 我的卷积神经网络结构 实验效果 训练时间次数及准确率 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 “备”则“倍” 有准备、有规划的人生更精彩！ A Hand-writing digit recognition Application base on Neural network and covolutional neural network NN digit recognition 1. Background 2. Method neural network back-propagation 3. Experiment training and testing samples 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, 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: Intel core i7 3630QM, 2.4GHZ Memory: 8G Byte Software: OS: windows 7 (64) IDE: vs2010 (C++) Experiment Experiment-Training and testing Samples Training and testing samples are from MNIST ，/exdb/mnist/ Every pic is a 28*28 dot matrix There are 10 pics in a sample, and there are 891 samples  Experiment Neural network design Our neural network has 3 layers： Layer Input layer Hidden layer Output layer Dimension 14*14=196 196 10 meaning Average grey value of four neighbor dots Empirical value , about 1~1.5 times of the input Target numbers , I.e. 0,1,2,3….9 Experiment neural network design BP neural network Experiment results Training samples： Testing samples： Training items Sample pics Right prediction Right ratio Training time value 7000 68