Quantum Machine Learning
Quantum machine learning (QML) aims to leverage the unique properties of quantum computers to enhance machine learning algorithms, primarily focusing on improving speed, accuracy, and data efficiency. Current research emphasizes the development and application of quantum algorithms like variational quantum circuits (VQCs), quantum kernels, and quantum neural networks (QNNs), including variations such as quantum LSTMs and GANs, often in hybrid quantum-classical architectures. This field is significant because it explores the potential for quantum speedups in various machine learning tasks, with applications ranging from image classification and drug discovery to materials science and anomaly detection, although the extent of practical quantum advantage remains an active area of investigation. Challenges include mitigating noise in quantum hardware and understanding the generalization capabilities of QML models.
Papers
Assessing the Impact of Noise on Quantum Neural Networks: An Experimental Analysis
Erik B. Terres Escudero, Danel Arias Alamo, Oier Mentxaka Gómez, Pablo García Bringas
Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation
Mohammad Junayed Hasan, M. R. C. Mahdy
Hierarchical Learning for Quantum ML: Novel Training Technique for Large-Scale Variational Quantum Circuits
Hrant Gharibyan, Vincent Su, Hayk Tepanyan
Quantum-Enhanced Support Vector Machine for Large-Scale Stellar Classification with GPU Acceleration
Kuan-Cheng Chen, Xiaotian Xu, Henry Makhanov, Hui-Hsuan Chung, Chen-Yu Liu
3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds
Lakshika Rathi, Edith Tretschk, Christian Theobalt, Rishabh Dabral, Vladislav Golyanik
Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures
Michael Kölle, Jonas Maurer, Philipp Altmann, Leo Sünkel, Jonas Stein, Claudia Linnhoff-Popien