Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Hyperparameter optimization for nn_ensemble backend #435

Open
osma opened this issue Jul 28, 2020 · 0 comments · May be fixed by #569
Open

Hyperparameter optimization for nn_ensemble backend #435

osma opened this issue Jul 28, 2020 · 0 comments · May be fixed by #569
Labels
enhancement
Milestone
Short term

Comments

@osma
Copy link
Member

osma commented Jul 28, 2020

Implement support for the hyperopt command for the nn_ensemble backend. Part of #240.

There are actually not that many hyperparameters in nn_ensemble (only nodes, dropout_rate and epochs) so this should be rather easy. epochs is a bit special since it may make sense to train incrementally, one epoch at a time, and evaluate the model between the epochs. So it's not necessarily an up-front choice.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement
Projects
None yet
Milestone
Short term
Development

Successfully merging a pull request may close this issue.

Hyperparameter optimization for NN ensemble NatLibFi/Annif
1 participant
@osma