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

Sketchy Loss Functions #4

Closed
twhughes opened this issue Dec 7, 2018 · 2 comments
Closed

Sketchy Loss Functions #4

twhughes opened this issue Dec 7, 2018 · 2 comments
Labels
bug Something isn't working

Comments

@twhughes
Copy link
Member

twhughes commented Dec 7, 2018

When I train simple linear models, the loss function oscillates wildly. For example, using inSituAdam:

image

model_linear = neu.Sequential([
    neu.ClementsLayer(N),
    neu.Activation(neu.Abs(N)),
    neu.DropMask(N, keep_ports=range(N_classes))
])

losses = neu.InSituAdam(model_linear, neu.CategoricalCrossEntropy, step_size=step_size).fit(x_train_flattened, y_train_onehot, epochs=n_epochs, batch_size=batch_size)

This may be a sign that the gradients are incorrect. Should double check.
@twhughes twhughes added the bug Something isn't working label Dec 7, 2018
@twhughes
Copy link
Member Author

I think its fine. This is probably due to the way the batching works.

@sunilkpai
Copy link
Collaborator

Just got this email notif, I don't think you would get this issue if you removed the abs nonlinearity and did a meansquareerror loss.

@sunilkpai sunilkpai reopened this Dec 21, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@twhughes @sunilkpai