Bend the Boundary

Learn about bendable decision boundaries.

Trace boundary with more than just a straight line

Let’s switch from the perceptron to the neural network. What does its decision boundary look like?

If we try the neural network on the linearly separable dataset, we’ll find that it gets the same perfect accuracy as the perceptron and a similarly straight decision boundary. However, on the non-linearly separable data, things get interesting.

Here’s the code that trains the neural network on the non linearly separable dataset:

Get hands-on with 1200+ tech skills courses.