Abstract

The perceptron is a binary classifier that learns an explicit decision boundary from an example set of labelled data, which can then be used to classify new, previously unseen, data. The perceptron is the first published and arguably the simplest artificial neuron, which is the class of models that form the literal basic unit of neural networks and deep learning. The perceptron forms an ideal introductory concept to these topics because of its simplicity.

It's a multi-part series in which I am planning to cover the following:

1. What is perceptron?
2. Core Idea
3. Geometric Interpretation
4. Perceptron Learning Algorithm
5. Convergence and Limitation