Feb 11, 2025 · Feb 9, 2025
diff --git a/content/tutorial-deep-learning-on-mnist.md b/content/tutorial-deep-learning-on-mnist.md

 ## 1. Load the MNIST dataset

 In this section, you will download the zipped MNIST dataset files originallystored in [Yann LeCun'swebsite](http://yann.lecun.com/exdb/mnist/). Then, you will transform them into 4 files of NumPy array type using built-in Python modules. Finally, you will split the arrays into training and test sets.
 In this section, you will download the zipped MNIST dataset files originallydeveloped byYann LeCun'sresearch team. (More details of the MNIST dataset are available on [Kaggle](https://www.kaggle.com/datasets/hojjatk/mnist-dataset).) Then, you will transform them into 4 files of NumPy array type using built-in Python modules. Finally, you will split the arrays into training and test sets.

 **1.** Define a variable to store the training/test image/label names of the MNIST dataset in a list:
Original file line number	Diff line number	Diff line change
Expand Up		@@ -62,7 +62,7 @@ This tutorial can be run locally in an isolated environment, such as [Virtualenv

		## 1. Load the MNIST dataset

		In this section, you will download the zipped MNIST dataset files originallystored in [Yann LeCun'swebsite](http://yann.lecun.com/exdb/mnist/). Then, you will transform them into 4 files of NumPy array type using built-in Python modules. Finally, you will split the arrays into training and test sets.
		In this section, you will download the zipped MNIST dataset files originallydeveloped byYann LeCun'sresearch team. (More details of the MNIST dataset are available on [Kaggle](https://www.kaggle.com/datasets/hojjatk/mnist-dataset).) Then, you will transform them into 4 files of NumPy array type using built-in Python modules. Finally, you will split the arrays into training and test sets.

		1. Define a variable to store the training/test image/label names of the MNIST dataset in a list:

Expand Down