From a9c24502bcdbf4a6b83477fdf7b3c4b3b86f7084 Mon Sep 17 00:00:00 2001
From: Giuseppe Saccardi <giuseppesaccardi@icloud.com>
Date: Thu, 6 May 2021 09:21:26 +0200
Subject: [PATCH] Update 12-3.md

Self-Attention Paragraph Typos: Issues #779
---
 docs/en/week12/12-3.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/week12/12-3.md b/docs/en/week12/12-3.md
index 6b7149760..c486ea881 100644
--- a/docs/en/week12/12-3.md
+++ b/docs/en/week12/12-3.md
@@ -36,7 +36,7 @@ $$
 \boldsymbol{h} = \boldsymbol{X} \boldsymbol{a}
 $$
 
-where $\boldsymbol{a} \in \mathbb{R}^n$ is a column vector with components $\alpha_i$.
+where $\boldsymbol{a} \in \mathbb{R}^t$ is a column vector with components $\alpha_i$.
 
 Note that this differs from the hidden representation we have seen so far, where the inputs are multiplied by a matrix of weights.