Autograd andBackpropagation in Pytorch

Have you ever used the following three lines of code, or some variation of them, in your ML scripts and had no clue what their purpose was? If so, this article should aid in clearing up and simplifying the truth behind these three tremendously important lines of code. Before I dive into the explanation, I want to clarify some prerequisite knowledge that is necessary to understand the contents of this article. Firstly, a working understanding of backpropagation and gradient descent is highly suggested. And by highly suggested, I mean mandatory. I know that both these concepts are taboo for coders who just want to code, but there is a lot of merit in understanding what is going on behind the scenes of your ML scripts.