In this chapter you will learn about a list of simple tricks which prove very effective while training our network. You will come across terms like weight regularization, early stopping, dropouts, feature augmentation, feature normalizations. All are very simple but crucial techniques. Take a quick look.
Practice 10: You will find a streamlit based chapter at https://github.com/jhilikb/UCS668
Prerequisite: Make sure that you have the Regularization folder in your course folder UCS668.
Start your python environment (say ucs668) that you set up (in Lab0) for the course using source ucs668/bin/activate (on your terminal if you use Linux/Mac) or using .\ucs668\Scripts\Activate.ps1 (on your powershell if using windows). In both cases you should be in the folder where you created the environment
cd Regularization
streamlit run reg.py
You will see the chapter start on your browser. In your browser, you can now explore the example tasks and understand how to solve them.