Gradient Descent, Step-by-Step

Gradient Descent is the workhorse behind most of Machine Learning. When you fit a machine learning method to a training dataset, you're probably using Gradient Descent. It can optimize parameters in a wide variety of settings. Since it's so fundamental to Machine Learning, I decided to make a "step-by-step" video that shows you exactly how it works.

It explains the purpose of each step of calculation. For example, the reason of why I am calculating the step size is to know how close I am to the minimum value. The narrator repeatedly refers back the graphs and previous values, comparing the differences between current and previous step, mentioning the purpose of doing so. It helped me understand how to find the best linear regression line that fits the data.