XOR Neural Network Visualizer

Untrained
Decision Space (2D) Grid: [0,1] × [0,1]
0
Epoch
0.5000
Loss (MSE)
50%
Accuracy
0 ep/s
Speed
Network Architecture & Weights 2 → Hidden → 1
Input (X1, X2)TargetOutputStatus
Why XOR is special: A single perceptron can only learn linearly separable functions (like AND, OR). It fails on XOR because no single straight line can separate `(0,1)` and `(1,0)` from `(0,0)` and `(1,1)`. Adding a non-linear hidden layer transforms the 2D coordinate space into a higher-dimensional representation where the classes become linearly separable.
Super generates helpful tools and automates fact-checking across the internet proactively. If you enjoyed this tool, build your own with Super and share it with a friend.