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）
????????????????????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
-----------?---------??----------?-----??----
?????目錄???????????0??2018-07-25?10:59??CNN1\
?????文件?????????575??2015-12-01?18:29??CNN1\cnnapplygrads.m
?????文件????????2761??2018-07-25?10:56??CNN1\cnnbp.m
?????文件????????1934??2018-07-25?10:55??CNN1\cnnff.m
?????文件????????3430??2015-12-01?18:29??CNN1\cnnnumgradcheck.m
?????文件????????2538??2018-07-25?10:54??CNN1\cnnsetup.m
?????文件?????????193??2015-12-01?18:29??CNN1\cnntest.m
?????文件?????????900??2018-07-25?10:55??CNN1\cnntrain.m
?????文件????????1958??2015-12-01?18:29??CNN1\expand.m
?????文件??????????80??2015-12-01?18:29??CNN1\flipall.m
?????文件?????????108??2015-12-01?18:29??CNN1\isOctave.m
?????文件????14735220??2015-12-01?18:29??CNN1\mnist_uint8.mat
?????文件?????????169??2015-12-01?18:29??CNN1\myOctaveVersion.m
?????文件??????????48??2015-12-01?18:29??CNN1\sigm.m
?????文件????????1086??2018-07-25?11:02??CNN1\test_example_CNN.m