Artificial Intelligence for Big Data

Non-linearities

Let's consider two types of feature spaces, where x1 and x2 are independent variables and y is a dependent variable that takes a values based on x1 and x2:

In the first instance, the input features are linearly separable with a straight line that represents the separation boundary. In other words, the space is linearly separable. However, in the second instance, the features space is inconsistent and cannot be separated with a line. We need some type of nonlinear or quadratic equation in order to derive the decision boundary. Most of the real-world scenarios are represented with the second type of feature space.

The deep neural ...