Perceptron

The perceptron is where machine learning began. Watch it nudge a line into place, point by point, until it separates the two classes.

PerceptronLive

the simplest learning machine

Controls

Presets

Class separation

Learning rate

The perceptron — the ancestor of every neural network — nudges a straight boundary each time it misclassifies a point. If the two classes are linearly separable it is guaranteed to find a dividing line; if they overlap, it never quite settles. Educational tool.

▶ Run in Python

Data Inspector

Modellinear classifier

Converges?yes (separable)

Governing equation

\overset{y}{^} = step (w \cdot x + b), w \leftarrow w + 0.10 (y - \overset{y}{^}) x

Reading this result: Moderate separation with a gentle learning rate: the boundary drifts steadily toward a clean split over many passes.

Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.

or unlock everything with Pro →

★ Sign in to save this setup

Save your tuned setup, or drop this simulation into your own site, docs, or course page.

How it works

A perceptron adjusts its weights whenever it misclassifies a training point, rotating and shifting a linear boundary. For linearly separable data it provably converges; for overlapping classes it oscillates forever — the limitation that motivated multi-layer networks. Educational tool.

✦

Ask the AI about this model

The math, the assumptions, real-world uses, or a code translation — explained for this exact simulation.

More CS / AI simulations

A* Pathfinding Maze Generator Neural Network k-Means Clustering Convex Hull L-System Fractals Turing Machine Image Convolution

Frequently asked questions

Is this perceptron simulator tool really free?▾

Yes. Perceptron runs entirely in your browser using your device's own compute, so local use is free forever. You only pay Compute Tokens if you scale a job to the cloud.

Do I need to install anything?▾

No. Everything runs client-side in a modern browser — no downloads, no license, no account required to start.

Can I save or share my simulation?▾

Create a free account to save projects, and use a shareable embed or minted DOI to publish a live, interactive version anywhere.

How accurate are the results?▾

The solver uses established numerical methods, but results are for research and educational purposes and should be validated against experiment or professional review before you rely on them.