Quantum Machine Learning (QML) leverages the principles of quantum mechanics—superposition and entanglement—to process data in high-dimensional Hilbert spaces, potentially solving certain ML problems exponentially faster than classical supercomputers.
Module 1: Parameterized Quantum Circuits (PQCs)
In QML, neural networks are replaced or augmented by PQCs. Classical data is encoded into quantum states (feature maps), processed by quantum gates with tunable parameters, and measured to produce classical outputs, optimized via classical gradient descent.