Do I need to install anything?

No. It runs in any modern browser, free, with no account required.

For Engineers · Deep Net Playground

Deep Net Playground for an A/B test

Built for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed. Simulate an A/B test live below — adjust the inputs and watch it respond, right in your browser.

Neural Net

open full solver →

Neural Network PlaygroundLive

2-layer MLP · live backprop

Controls

Presets

Hidden neurons

Learning rate

Speed1×

A tiny multilayer perceptron trained by real backpropagation. The background shows its learned decision boundary; dots are the training data, colored by true class.

▶ Run in Python

Data Inspector

Epoch0

Loss0.0000

Architecture2→8→1

Governing equation

a = tanh (W_{1} x + b_{1}), \overset{y}{^} = σ (W_{2} a + b_{2}), L = 0.0000

Reading this result: With 8 hidden units the net bends the boundary into curves — more units capture finer shapes like the spiral, but too many can overfit.

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

↓

Gradient Descent

open full solver →

Gradient Descent StudioLive

optimization on a loss landscape

Controls

Watch gradient descent (with momentum) roll downhill on different loss landscapes. Too high a learning rate overshoots.

Presets

Learning rate

Momentum

▶ Run in Python

Data Inspector

Surfaceripple

Step0/200

Optimizermomentum GD

Governing equation

x_{k + 1} = x_{k} - η \nabla f (x_{k}), η = 3

Reading this result: A learning rate of 3 is well matched to the curvature here: steps are large enough to make progress yet small enough to avoid overshoot, giving a smooth, roughly quadratic descent toward the minimum.

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

or unlock everything with Pro →

Also for:Students Researchers Educators Hobbyists & Makers K-12 Students First Responders General version →

More with Deep Net Playground

Deep Net Playground for a survey sample Deep Net Playground for a poll margin Deep Net Playground for a quality-control chart Deep Net Playground for a clinical trial Deep Net Playground for a customer churn Deep Net Playground for a click-through rate Deep Net Playground for an exam-score curve Deep Net Playground for a defect rate

Frequently asked questions

Is this good for engineers?: Yes — this version of "Deep Net Playground for an A/B test" is framed for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed.
Do I need to install anything?: No. It runs in any modern browser, free, with no account required.