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.
How to tune hyperparameters for LSTM training.
17 views (last 30 days)
Show older comments
Badavath Purnesh Singh
on 5 Nov 2021
Answered: David Willingham
on 5 Nov 2021
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. ![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/790759/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/790759/image.png)
Accepted Answer
David Willingham
on 5 Nov 2021
Hi,
I'd recommend using the Experiment Manager App for tuning / understanding various hyperparameter combinations.
0 Comments
More Answers (0)
See Also
Categories
Find more on Classification in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!