Artificial Intelligence By Example

Quadratic loss function

For gradient descent, see Chapter 5, Manage the Power of Machine Learning and Deep Learning. Let us refresh the concept. Imagine you are on a hill and want to walk down that hill. Your goal is to get to y, the bottom of the hill. Presently you are at a. Google Maps shows you that you still have to go a certain distance:

That formula is great for the moment. But now suppose you are almost at the bottom of the hill, and the person walking in front of you dropped a coin. You have to slow down now, and Google Maps is not helping much because it doesn't display such small distances that well. You open an imaginary application ...