Quantum Machine Learning & Quantum AI

My QML research asks when quantum models, quantum-inspired representations, or quantum-generated parameters can provide useful inductive bias under realistic data, hardware, and deployment constraints. The emphasis is not only accuracy, but also parameter efficiency, scalability, robustness, and classical deployability.

Representative topics include:

• quantum kernel learning and tensor-network simulation of large-qubit QSVMs;
• quantum parameter adaptation for climate and typhoon trajectory forecasting;
• photonic quantum-enhanced knowledge distillation;
• quantum-inspired Kolmogorov–Arnold and tensor-network models for scientific machine learning;
• QML for anomaly detection, medical neuroimaging, PCB defect detection, and IoT time-series.

Selected outputs: Machine Learning: Science and Technology 2025, IEEE QCE 2025, QCNC 2026, ICASSP 2025.