From 84c6324c5fdbae1a5fe05cd6ce9e9aa05b20026f Mon Sep 17 00:00:00 2001
From: Yaseen <9275716+ynx0@users.noreply.github.com>
Date: Sun, 12 Jul 2020 07:58:36 -0400
Subject: [PATCH] Fix typo
---
_pages/bingham-rotation-learning.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/_pages/bingham-rotation-learning.md b/_pages/bingham-rotation-learning.md
index 94b40c4..8c15293 100644
--- a/_pages/bingham-rotation-learning.md
+++ b/_pages/bingham-rotation-learning.md
@@ -13,7 +13,7 @@ youtubeId: 8QMcNmCPYR0
[ 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 smoothness property 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 belief (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 smoothness property 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 belief (or distribution) over rotations.
{::nomarkdown}