04. How Computers Interpret Images

As you follow along this lesson, you are encouraged to open the referenced Jupyter notebooks. We will present a solution to you, but please try creating your own deep learning models! Much of the value in this experience will come from playing around with the code in your own way.

In order to get up and running, please clone the materials from the GitHub repository by executing the following command in the terminal: git clone https://github.com/udacity/aind2-cnn.git. Follow the instructions in the repository to set up the Conda environment and install the necessary dependencies.

To open the notebook referenced in this video, navigate to the mnist-mlp/ folder and open mnist_mlp.ipynb.

Additional Note

The MNIST database is arguably the most famous database in the field of deep learning! Check out this figure that shows datasets referenced over time in NIPS papers.