So far, we have seen the basics of neural networks and how the learning portion works. In this chapter, we take a look at one of the basic and simple forms of neural network architecture, the perceptron.

A perceptron is defined as a basic building block of a neural network. In machine learning, a perceptron is an algorithm for supervised learning of binary classifiers. They classify an output as binary: TRUE/FALSE or 1/0.

This chapter helps understand the following topics:

• Explanation of the perceptron
• Linear separable classifier
• Simple perceptron implementation function
• Multi-Layer Perceptrons (MLPs)

By the end of the chapter, we will understand the basic concepts of perceptrons and how they are used in neural network algorithm. We will discover the linear separable classifier. We will learn a simple perceptron implementation function in R environment. We will know how to train and model an MLP.