Home▸AI & Machine Learning▸Backpropagation Playground: Decision Boundaries and Loss Curves in 2D

Backpropagation Playground: Decision Boundaries and Loss Curves in 2D

The same live network in 2D: weights as coloured edges, a probe point sweeping the plane to light up the neurons, a decision map over the training data, and loss and accuracy curves. Shared model with the 3D scene, with gradient and XOR numerical checks.

AI & Machine Learning2DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 3D version
Backpropagation Playground: Decision Boundaries and Loss Curves in 2D ↗ Open standalone

Train a real multilayer perceptron live by backpropagation. Pick XOR, a disc in a ring, two moons or two spirals, change width, activation, learning rate and noise, and watch the weights, the forward-pass activations of a moving probe, the loss curve and the decision map evolve. A Blender-built network on a plinth with a display, and numerical gradient checks built in.

⚙ Under the hood

The same live network in 2D: weights as coloured edges, a probe point sweeping the plane to light up the neurons, a decision map over the training data, and loss and accuracy curves. Shared model with the 3D scene, with gradient and XOR numerical checks.

Neural NetworksBackpropagationMultilayer PerceptronDecision BoundaryGradient Descent

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)