# Perceptron

> An early machine from 1958. It learned to sort things by changing its weights.

**Field:** Artificial Intelligence  
**Category:** Foundations  
**Also known as:** Rosenblatt Perceptron, Single-Layer Perceptron

## Think of it like

It is like a vote. Each clue counts for a bit, and if the total is big enough, the answer is yes.

## Definition

The perceptron is one of the first machines that learned from examples. Frank Rosenblatt described it in 1958. It adds up its inputs, each with its own weight, and says yes if the total passes a set line. When it gets an answer wrong, it moves the weights a little. A single perceptron can only split data with a straight line, so it fails on many tasks.

## Example

A perceptron learns to sort shapes on a card into two groups. After each wrong answer it shifts its weights, and soon it sorts most cards right.

## Why it matters

It is the simple building block that grew into today's neural networks. Stack many of them in layers and you get deep learning.

## Common mistake

Thinking one perceptron can learn anything. On its own it only draws a straight line between two groups.

## Three principles

- **Weighted sum.** Each input counts by its weight.
- **Learns from mistakes.** Wrong answers nudge the weights.
- **One straight line.** Layers are needed for more.

## Related terms

- [Artificial Neuron](https://learn.benibix.com/term/ai/artificial-neuron)
- [Multilayer Perceptron (MLP)](https://learn.benibix.com/term/ai/multilayer-perceptron)
- [Neural Network](https://learn.benibix.com/term/ai/neural-network)
- [Activation Function](https://learn.benibix.com/term/ai/activation-function)
- [Deep Learning](https://learn.benibix.com/term/ai/deep-learning)

## Told apart from

- [Perceptron vs Multilayer Perceptron](https://learn.benibix.com/compare/perceptron-vs-multilayer-perceptron): People think a multilayer perceptron is just a big perceptron. It is more than that. One perceptron adds up its inputs and says yes or no, so it can only split data with a straight line. A multilayer perceptron stacks many of them in layers, with a bend in each one. The layers let it learn curved and tangled patterns that one perceptron never can.

## Taught in

- [Dartmouth and the AI Winters](https://learn.benibix.com/learn/ai-foundations/dartmouth-and-the-ai-winters): AI Basics, 8/10

![A timeline with five marks. 1958, the perceptron learns from examples. 1966, ELIZA chats by matching words. 1997, Deep Blue beats the world chess champion. 2010, the ImageNet contest starts. 2016, AlphaGo beats a top Go player 4 to 1.](https://learn.benibix.com/diagrams/ai8-ai-milestones.svg)

---

Source: https://learn.benibix.com/term/ai/perceptron
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
