Reverse Engineering traingd in ANN?

1 view (last 30 days)
Kannan
Kannan on 19 Mar 2014
Commented: Greg Heath on 28 Mar 2014
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!

Answers (1)

Greg Heath
Greg Heath on 20 Mar 2014
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 Comments
Kannan
Kannan on 28 Mar 2014
Hurray! Successfully calculated 'change in weight/bias' for the output layer. Moving on to hidden layer now.

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!