function?net?=?cnnapplygrads（net?opts）
%?使用梯度下降算法進行參數訓練
%?該函數完成權重修改，更新模型的功能
%?1更新特征抽取層的權重?weight+bias
%?2?更新末尾單層感知機的權重?weight+bias

????for?l?=?2?:?numel（net.layers）
????????if?strcmp（net.layers{l}.type?‘c‘）%只更新卷積層的參數？沒有更新下采樣層的參數？
????????????for?j?=?1?:?numel（net.layers{l}.a）
????????????????for?ii?=?1?:?numel（net.layers{l?-?1}.a）
????????????????????net.layers{l}.k{ii}{j}?=?net.layers{l}.k{ii}{j}?-?opts.alpha?*?net.layers{l}.dk{ii}{j};
????????????????end
????????????????net.layers{l}.b{j}?=?net.layers{l}.b{j}?-?opts.alpha?*?net.layers{l}.db{j};
????????????end
????????end
????end

????net.ffW?=?net.ffW?-?opts.alpha?*?net.dffW;
????net.ffb?=?net.ffb?-?opts.alpha?*?net.dffb;
end

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件????????766??2015-02-20?19:53??yhw-CNN\cnnapplygrads.m

?????文件???????2414??2015-02-20?19:47??yhw-CNN\cnnbp.asv

?????文件???????2711??2017-02-10?13:57??yhw-CNN\cnnbp.m

?????文件???????2001??2015-02-18?00:17??yhw-CNN\cnnff.asv

?????文件???????2521??2017-02-10?13:39??yhw-CNN\cnnff.m

?????文件???????3430??2014-05-11?05:46??yhw-CNN\cnnnumgradcheck.m

?????文件???????2372??2015-02-17?00:01??yhw-CNN\cnnsetup.asv

?????文件???????2389??2015-02-17?00:18??yhw-CNN\cnnsetup.m

?????文件????????329??2015-02-17?00:24??yhw-CNN\cnntest.m

?????文件???????1194??2015-02-17?09:49??yhw-CNN\cnntrain.asv

?????文件???????1261??2017-02-09?18:34??yhw-CNN\cnntrain.m

?????文件???????1958??2014-05-11?05:46??yhw-CNN\expand.m

?????文件?????????80??2014-05-11?05:46??yhw-CNN\flipall.m

?????文件????????108??2014-05-11?05:46??yhw-CNN\isOctave.m

?????文件????????169??2014-05-11?05:46??yhw-CNN\myOctaveVersion.m

?????文件?????????48??2014-05-11?05:46??yhw-CNN\sigm.m

?????文件???????2030??2017-02-10?16:21??yhw-CNN\test_example_CNN.asv

?????文件???????1072??2014-05-11?05:46??yhw-CNN\visualize.m

?????文件???????7640??2017-02-10?20:32??yhw-CNN\mnist_uint8_yhw.mat

?????文件???????2445??2017-02-10?12:21??yhw-CNN\cnnff2.m

?????文件????????341??2017-02-10?12:20??yhw-CNN\cnntest2.m

?????文件???????3502??2017-02-10?20:39??yhw-CNN\test_example_CNN_yhw.m

?????文件????????252??2017-02-10?09:34??yhw-CNN\樣本生成mat格式\鏍鋒湰瀛椾綋璇存槑.txt

?????文件????????663??2017-02-10?09:29??yhw-CNN\樣本生成mat格式\101.jpg

?????文件????????803??2017-02-10?09:30??yhw-CNN\樣本生成mat格式\102.jpg

?????文件????????804??2017-02-10?09:30??yhw-CNN\樣本生成mat格式\103.jpg

?????文件????????791??2017-02-10?09:30??yhw-CNN\樣本生成mat格式\104.jpg

?????文件????????845??2017-02-10?09:30??yhw-CNN\樣本生成mat格式\105.jpg

?????文件????????831??2017-02-10?09:31??yhw-CNN\樣本生成mat格式\106.jpg

?????文件????????738??2017-02-10?09:31??yhw-CNN\樣本生成mat格式\107.jpg

............此處省略133個文件信息