what is the value for L2 regularization coeff, by default,while training?

2 views (last 30 days)
while trainig a deep learning network in MATLAB, what is the trainingOptions for setting L2 regularization coeff.?
Like if adam optimizer is used how to set this parameter?
more clearly like in optim.Adam in pytorch , weight_decay option is given.how to set it here in MATLAB?

Answers (1)

Adam Danz
Adam Danz on 21 Oct 2020
I think you're looking for the L2Regularization Solver Option.
  6 Comments
krishna Chauhan
krishna Chauhan on 22 Oct 2020
Ya even I was thinking they are same,
for your second suggestion,,,,,,,,,,I m giving same input to both the models but getting entirely different accuaracy. In MATLAB 80% while in Pytorch they got only 50- 55%
though Pytorch has no option for padding='same' may be this is the issue.
I am confused what to do now?
Adam Danz
Adam Danz on 22 Oct 2020
Edited: Adam Danz on 27 Oct 2020
If it were me, I'd step through the process in debug mode to study and compare the two methods. Perhaps there's more detail in Matalb's (and PyTorch's) documentation that would shed light on the differences.
Maybe the difference is caused by a small difference in one of the optional parameters, as you mentioned.

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!