The objective function

It is time for the third building block of the machine learning algorithm.

The objective function the objective function is the measure used to evaluate how well the models outputs

match the desired correct values.

In this lesson we will elaborate on that objective functions are generally split into two types.

Loss functions and reward functions loss functions are also called cost functions.

The lower the loss function the higher the level of accuracy of the model.

Most often we work with loss functions.

An intuitive example is a loss function that measures the error of prediction.

We want to minimize the error of prediction thus minimize the loss reward functions.

On the other hand are basically the opposite of loss functions.

The higher the reward function the higher the level of accuracy of the model usually reward functions

are used in reinforcement learning where the goal is to maximize a specific result.

Remember the algorithm we mentioned earlier the one playing Super Mario the score obtained by the algorithm

while playing the game is the reward function maximizing the final score would mean maximizing the reward

function.

All right when dealing with supervised learning we normally encounter loss functions.

Therefore in this course we’ll deal mostly with them in our next video.

We will explore the two most common loss functions.

Thanks for watching.