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.

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 ability to backprop errors to input (for model interrogation) #2866

Closed
turambar opened this issue Feb 14, 2017 · 4 comments

Comments

@turambar
Copy link

commented Feb 14, 2017

Placeholder issue. Will add more detailed description later, but TL;DR: we'd like to be able to ask the model what kind of inputs (e.g., image) will maximize the output (e.g., probability that image is cat) and solve for this using gradient descent in the input space (vs. weight space during learning).

@turambar turambar assigned turambar and unassigned turambar Feb 14, 2017

@turambar

This comment has been minimized.

Copy link
Author

commented Feb 14, 2017

@AlexDBlack: as we discussed previously

@raver119

This comment has been minimized.

Copy link
Contributor

commented Apr 27, 2018

Is this issue still relevant?

@AlexDBlack

This comment has been minimized.

Copy link
Contributor

commented Apr 27, 2018

@lock

This comment has been minimized.

Copy link

commented Sep 22, 2018

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.

@lock lock bot locked and limited conversation to collaborators Sep 22, 2018

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
3 participants
You can’t perform that action at this time.