Home › Glossary › Neural Networks › Perceptron

Beginner · Neural Networks

Perceptron

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A simple algorithm for supervised learning of binary classifiers, forming a basic type of artificial neuron.

Technical Definition

A simple algorithm for supervised learning of binary classifiers, forming a basic type of artificial neuron.

How it works

The perceptron is one of the earliest and simplest types of artificial neural networks. It's a linear binary classifier, meaning it can learn to separate data into two categories based on a linear decision boundary. While limited, it laid the groundwork for more complex neural networks.

Related Concepts

  • Supervised Learning — Learning from input–output pairs where each training example carries a correct label.

Further Reading

  • Wikipedia — Glossary of AI