Search⌘ K

Partial Derivatives

Explore the concept of partial derivatives and how they enable gradient descent on functions with multiple variables. Understand how to calculate gradients with respect to each parameter and apply these to optimize loss in machine learning models.

Review loss function

Take a look at the loss function in math notation again:

L=1mi=1m((wxi+b)yi)2\large{ L=\frac{1}{m}\sum_{i=1}^{m}((wx_i+b)-y_i)^2 }

So far, we treated all the values in this function as constants, except for ww. In particular, we fixed bb at a value of 0. If we change ...