Quantum Data Re-uploading Classifier

A single qubit, reset to |0⟩ and re-encoded with the same 2D input point across several layers, is enough to learn a nonlinear decision boundary — a result from the "data re-uploading" family of quantum machine-learning circuits. This simulator runs a real single-qubit statevector through L trainable layers, trains the rotation angles with the exact parameter-shift-rule gradient (no classical backprop through the quantum state), and renders both the live Bloch-sphere trajectory of whatever point you hover and the resulting classification tiles across the input plane, so you can watch a genuinely quantum-native optimizer sculpt a decision boundary in real time.