完整的CNN卷积神经网络

完整的CNN卷积神经网络，可用于图像等领域，有很好的指导。

function net = cnnapplygrads（net opts）  
    for l = 2 : numel（net.layers）  
        if strcmp（net.layers{l}.type ‘c‘）  
            for j = 1 : numel（net.layers{l}.a）  
                for ii = 1 : numel（net.layers{l - 1}.a）  
                    % 这里没什么好说的，就是普通的权值更新的公式：W_new = W_old - alpha * de/dW（误差对权值导数）  
                    net.layers{l}.k{ii}{j} = net.layers{l}.k{ii}{j} - opts.alpha * net.layers{l}.dk{ii}{j};  
                end  
            end  
            net.layers{l}.b{j} = net.layers{l}.b{j} - opts.alpha * net.layers{l}.db{j};  
        end  
    end  
  
    net.ffW = net.ffW - opts.alpha * net.dffW;  
    net.ffb = net.ffb - opts.alpha * net.dffb;  
end  

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        731  2016-10-01 05:31  deep learning\cnnapplygrads.m

     文件       3851  2016-10-01 05:30  deep learning\cnnbp.m

     文件       1774  2016-10-01 11:23  deep learning\cnnff.m

     文件       3590  2016-10-01 05:34  deep learning\cnnnumgradcheck.m

     文件       5235  2016-10-01 05:29  deep learning\cnnsetup.m

     文件        435  2016-10-01 05:31  deep learning\cnntest.m

     文件       1850  2016-10-01 13:20  deep learning\cnntrain.m

     文件       1620  2017-04-20 03:15  deep learning\Example119.m

     文件       1958  2016-10-01 08:24  deep learning\expand.m

     文件         80  2016-10-01 08:24  deep learning\flipall.m

     文件   13337300  2015-05-26 06:29  deep learning\mnist_all.mat

     文件   14735220  2016-10-01 08:24  deep learning\mnist_uint8.mat

     文件        435  2011-04-11 00:04  deep learning\New Folder\classification_evaluate.m

     文件        731  2016-10-01 05:31  deep learning\New Folder\cnnapplygrads.m

     文件        838  2016-10-04 01:09  deep learning\New Folder\cnnapplygrads119.m

     文件       3851  2016-10-01 05:30  deep learning\New Folder\cnnbp.m

     文件       3889  2016-10-04 01:14  deep learning\New Folder\cnnbp119.m

     文件       1774  2016-10-01 11:23  deep learning\New Folder\cnnff.m

     文件       1845  2016-10-04 01:09  deep learning\New Folder\cnnff119.m

     文件       3590  2016-10-01 05:34  deep learning\New Folder\cnnnumgradcheck.m

     文件       5235  2016-10-01 05:29  deep learning\New Folder\cnnsetup.m

     文件       5704  2016-10-05 07:07  deep learning\New Folder\cnnsetup119.m

     文件        437  2016-10-04 00:40  deep learning\New Folder\cnntest.m

     文件        405  2016-10-04 00:46  deep learning\New Folder\cnntest119.m

     文件       1850  2016-10-01 13:20  deep learning\New Folder\cnntrain.m

     文件       2030  2016-10-04 01:08  deep learning\New Folder\cnntrain119.m

     文件       1821  2017-05-30 00:12  deep learning\New Folder\Example119.m

     文件       1958  2016-10-01 08:24  deep learning\New Folder\expand.m

     文件         80  2016-10-01 08:24  deep learning\New Folder\flipall.m

     文件   13337300  2015-05-26 06:29  deep learning\New Folder\mnist_all.mat

............此处省略11个文件信息