-
Notifications
You must be signed in to change notification settings - Fork 12
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add regularization #11
Comments
Thanks Marvin, this improvement will help a lot! |
In my project I have 1 hidden layer. I've constructed a solution that loops through various architectures and finds the optimal number of nodes that minimizes the cross-validation error. Would that be considered a form of regularization similar to drop-out? |
No, I don't think so. Btw., I think we should have both dropout and L1/L2 regularization in the package. |
Is this still something that is in the pipeline? Thanks. |
I still think it would be nice to have it but we currently do not have the resources to further develop this package. A PR would be very much welcome! |
We should add some kind of regularization such as L2 regularization.
The text was updated successfully, but these errors were encountered: