Reverse Engineering traingd in ANN?

3 次查看(过去 30 天)
Kannan
Kannan 2014-3-19
评论: Greg Heath 2014-3-28
I am sort of trying to reverse engineer traingd algorithm. dWB = param.lr * gWB is the equation shown in traingd.m, would like to understand how gWB is calculated. Any reference/example/sourcecode/backpaper in this regard is much appreciated. Thanks in advance!

回答(1 个)

Greg Heath
Greg Heath 2014-3-20
type traingd
% Initialize
startTime = clock;
original_net = net;
[perf,vperf,tperf,gWB,gradient] = nntraining.perfs_grad(net,data,fcns);
...
...
% Gradient Descent
dWB = param.lr * gWB;
WB = WB + dWB;
net = setwb(net,WB);
[perf,vperf,tperf,gWB,gradient] = nntraining.perfs_grad(net,data,fcns);
>> help nntraining
Neural Network Toolbox Utility Functions
This directory contains utility functions. It is recommended these functions not be used as they may be removed or altered in future versions of this software.
So, search for the directory containing utility functions
Hope this help.
Thank you for formally accepting my answer
Greg
  4 个评论
Kannan
Kannan 2014-3-28
Hurray! Successfully calculated 'change in weight/bias' for the output layer. Moving on to hidden layer now.

请先登录,再进行评论。

类别

Help CenterFile Exchange 中查找有关 Image Data Workflows 的更多信息

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by