Skip to content
BENIBIX Learn

Perceptron

AI🧭 FoundationsAI History

Also known as Rosenblatt Perceptron, Single-Layer Perceptron

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

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.

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.

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.
The perceptron, 1958: the first mark on the road to neural networks.

Common mistake

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

Key takeaways

  1. 1
    Weighted sum. Each input counts by its weight.
  2. 2
    Learns from mistakes. Wrong answers nudge the weights.
  3. 3
    One straight line. Layers are needed for more.

Compare

Learn it properly