Network and decision map (live training)
Loss and accuracy vs epoch

Backpropagation Playground: Decision Boundaries and Loss Curves in 2D

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.

Made with 🟠 Blender