How to tune hyperparameters for LSTM training.

58 views (last 30 days)
I'm training a LSTM model for signal classificaiton. The training progress graph looks like the first pictiure at the very begininng and incrreases slowy. I think the model is over fitting or unddr fitting. I hope somone could resolve this issue.
  1 Comment
Badavath Purnesh Singh
Badavath Purnesh Singh on 5 Nov 2021
To let the algorithm train upto 95-99%, it is talking 3000 epochs. I have used 0.0001 as Learning rate and default mini batch value.

Sign in to comment.

Accepted Answer

David Willingham
David Willingham on 5 Nov 2021
Hi,
I'd recommend using the Experiment Manager App for tuning / understanding various hyperparameter combinations.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!