Skip to content

Fix typo #1

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

Open
ynx0 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix typo #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion _pages/bingham-rotation-learning.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ youtubeId: 8QMcNmCPYR0
[<i class="fa fa-github" aria-hidden="true"></i> View it on Github](https://github.com/utiasSTARS/bingham-rotation-learning){: .btn .btn-green }


There are many ways to represent rotations: Euler angles, rotation matrices, axis-angle vectors, or unit quaternions, for example. In deep learning, it is common to use unit quaternions for their simple geometric and alebraic structure. However, unit quaternions lack an important <strong>smoothness property</strong> that makes learning 'large' rotations difficult, and other representations are not easily amenable to learning uncertainty. In this work, we address this gap and present a smooth representation that defines a <em>belief</em> (or distribution) over rotations.
There are many ways to represent rotations: Euler angles, rotation matrices, axis-angle vectors, or unit quaternions, for example. In deep learning, it is common to use unit quaternions for their simple geometric and algebraic structure. However, unit quaternions lack an important <strong>smoothness property</strong> that makes learning 'large' rotations difficult, and other representations are not easily amenable to learning uncertainty. In this work, we address this gap and present a smooth representation that defines a <em>belief</em> (or distribution) over rotations.

{::nomarkdown}
<div style='text-align:center'>
Expand Down