Interactive module

Neural Network Visualizer

Watch a small feedforward network learn in real time — weights, activations, and the decision boundary all update live.

How it works

XOR — the classic non-linear problem. Class 0 lives in the top-left and bottom-right quadrants; class 1 in the other two. No straight line can separate them, so the hidden layer is essential.

x1x20.500.500.500.50ŷInputHidden (3)Output

Press Train to start, or use Step to advance one sample at a time.

step0samples seen
losslower = better
ŷ (prediction)0 = class 0, 1 = class 1
test lossheld-out sample
test accrunning average