Welcome to the Logistic Regression module!
Contrary to what the name suggest, Logistic Regression is used to tackle classification problems. Recapping, regression models predict numerical values given some inputs. Classification models, on the other hand, predict membership of a class based on some inputs.
For instance, the problem of predicting whether an animal in an image is a dog or a cat is a classification problem: the task is to, given an instance (a particular image of a dog or cat), determine whether it is part of the class "dog" or the class "cat".
Another example of a classification problem is the problem of predicting Iris species (the species of a type of flower called Iris) based on petal and sepal measurements. We have looked at this dataset in previous modules.
When logistic regression is applied to discriminate between 2 different classes, it is called binary logistic regression. When the number of classes is greater than 2 (i.e. a multiclass problem), then it is called multinomial logistic regression. Sometimes, it is also known as softmax regression, for reasons that will become evident in the next sections.
You will see how logistic regression is a natural extension to linear regression, making small modifications to the model so that it tackles classification problems.