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

Conjugate Gradient / Line Gradient do not work in Weka Cross Validation #18

Open
braun-steven opened this issue Nov 26, 2017 · 0 comments
Open

Conjugate Gradient / Line Gradient do not work in Weka Cross Validation #18

braun-steven opened this issue Nov 26, 2017 · 0 comments
Labels
bug

Comments

@braun-steven
Copy link
Member

Choosing CONJUGATE_GRADIENT or LINE_GRADIENT_DESCENT as optimization algorithm in NeuralNetworkConfiguration while performing a cross validation results in the following behavior:

  • First validation works properly (loss is reduced in each epoch)
  • Second and further validations' loss is static and does not reduce

TODO: Inspect weights/updates
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@braun-steven