From ae2bfc3e7fd2ea833cb484299b76b674e1361f05 Mon Sep 17 00:00:00 2001
From: Minh Dang <38881541+minhdang241@users.noreply.github.com>
Date: Thu, 7 May 2020 17:14:03 +0700
Subject: [PATCH] Update nn_tutorial.py

the description of @ is misleading. It should be maxtrix multiplication not dot product.
---
 beginner_source/nn_tutorial.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/beginner_source/nn_tutorial.py b/beginner_source/nn_tutorial.py
index 5f915a3d3ea..9f4af59ed7c 100644
--- a/beginner_source/nn_tutorial.py
+++ b/beginner_source/nn_tutorial.py
@@ -136,7 +136,7 @@ def model(xb):
     return log_softmax(xb @ weights + bias)
 
 ###############################################################################
-# In the above, the ``@`` stands for the dot product operation. We will call
+# In the above, the ``@`` stands for the matrix multiplication operation. We will call
 # our function on one batch of data (in this case, 64 images).  This is
 # one *forward pass*.  Note that our predictions won't be any better than
 # random at this stage, since we start with random weights.