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

Question: Use of cross country automatic differentiation #103

Open
MarisaKirisame opened this issue Jul 19, 2020 · 0 comments
Open

Question: Use of cross country automatic differentiation #103

MarisaKirisame opened this issue Jul 19, 2020 · 0 comments

Comments

@MarisaKirisame
Copy link

Mixed mode is very aesthetically pleasing because it is a generalization of both forward mode and reverse mode ad, thus unifying the two big approach in ad. However, I never found any case where I need an n*m size jacobian where both (n > 1) and (m > 1).

Do you guys have any use case for mixed mode?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@MarisaKirisame