Notebook: Batch Normalization

After learning about batch normalization and how it works, add it to a simple model and see how it improves convergence.

The next notebook will show you how a simple MNIST classification model improves with the addition of batch normalization layers. It is suggested that you read through the text in the notebook and run each cell to see the effects of batch normalization. You're also encouraged to create tests of your own with even more complex networks!

To open this notebook, you have two options:

• Go to the next page in the classroom (recommended).
• Clone the repo from Github and open the notebook Batch_Normalization.ipynb in the batch-norm folder. You can either download the repository with git clone https://github.com/udacity/deep-learning-v2-pytorch.git, or download it as an archive file from this link.

Instructions

• This is an example notebook, please carefully read the text in the notebook and run each cell to see how two different models (one with and one without batch normalization) perform