电子科技2019，Vol.32Issue(3)：53-56,66,5.DOI:10.16180/j.cnki.issn1007-7820.2019.03.011
一种改进的LeNet网络
An Improved LeNet Network
摘要
Abstract
Aiming at the problems of low learning efficiency, slow convergence and long training time in convolutional neural networks, this paper presented an improved LeNet convolutional neural network model. The model used a convolutional kernel whose convolution scale was set as 3 and stride was set as 2 instead of the original pooled layer, and added a batch normalization layer before each activation function layer. Experiments on the Mnist dataset showed that compared with the traditional LeNet network, the convolutional neural network proposed in this paper improved the accuracy rate and had faster convergence speed and shorter training time.关键词
图像分类/卷积神经网络/批量归一化/池化层/卷积核/随机梯度下降法Key words
image classification/convolutional neural network/batch normalization/pooling layer/convolution kernel/stochastic gradient descent分类
信息技术与安全科学引用本文复制引用
胡德敏,程普芳..一种改进的LeNet网络[J].电子科技,2019,32(3):53-56,66,5.基金项目
国家自然科学基金(61170277,61472256) （61170277,61472256）
上海市教委科研创新重点项目(12zz17) （12zz17）
上海市一流学科建设项目(S1201YLXK) （S1201YLXK）
