cnn_linear_max-master

代码说明：

  一个简单的卷积神经网络与线性神经元。 结构:输入- >卷积- > max池- >卷积- > max池- >完全连接。 编译c++马克斯池功能首先输入“墨西哥人MaxPooling.cpp”。 数据可以在http://ai.stanford.edu/下载~ amaas /数据/ data.zip 可以在http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset下载的数据加载函数 约98 为50时代的所有训练数据分类精度。(A simple convolutional neural network with linear neurons. Structure: input->convolution->max pooling->convolution->max pooling->fully connected. Compile the max pooling function in C++ first by typing mex MaxPooling.cpp . The data can be downloaded in http://ai.stanford.edu/~amaas/data/data.zip The data loading functions can be downloaded in http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset About 98 classification accuracy for 50 epochs of all training data.)

文件列表：

cnn_linear_max-master
.....................\cnnTest.m,1513,2014-01-17
.....................\cnnTrain.m,5574,2014-01-17
.....................\Debug
.....................\.....\MaxPooling.pch,340164,2015-04-01
.....................\.....\vc60.idb,41984,2015-04-01
.....................\.....\vc60.pdb,45056,2015-04-01
.....................\MaxPooling.cpp,8899,2015-04-01
.....................\MaxPooling.dsp,3449,2015-04-01
.....................\MaxPooling.dsw,528,2015-04-01
.....................\MaxPooling.ncb,41984,2015-04-01
.....................\MaxPooling.opt,48640,2015-04-01
.....................\MaxPooling.plg,1340,2015-04-01
.....................\README.md,487,2014-01-17
.....................\upsampleMax.m,142,2014-01-17