Quantum Computing for Multimedia Processing

6 units · Graduate

Intermittent: 6 units Quantum Computing for Multimedia Processing is a 6-unit Mini-2 course that introduces students to the principles, algorithms, and emerging toolchains of quantum computing (QC), with concrete applications to multimedia data: speech, audio, image, and video. The course is motivated by two convergent trends: (1) the exponential growth in compute and energy demand of modern multimedia pipelines, and (2) the rapid maturation of cloud-accessible quantum hardware and Python-native quantum machine learning (QML) libraries such as PennyLane, Qiskit, Cirq, TensorFlow Quantum, and Amazon Braket. The course balances theory and practice. Six lecture sessions develop the conceptual scaffolding: qubits and circuits, data encoding, quantum k-means, quantum neural networks, variational quantum circuits, quantum kernels and qSVMs, qubit hardware modalities, and the CPU/GPU/TPU/QPU compute landscape for multimedia workloads. Five hands-on lab sessions teach students to build, train, and benchmark quantum models on real and simulated devices using the leading open-source toolkits. A final poster session lets students present a small project applying a quantum algorithm to a multimedia task of their choice.