This tutorial introduces key concepts in Quantum Machine Learning (QML), covering qubits, gates, entanglement, parameterized circuits, and quantum neural networks (QNNs). It highlights recent advances in quantum-enhanced model compression and quantum architecture search (QAS), which improve QML efficiency and scalability. Attendees will gain hands-on experience with QML implementations on quantum simulators and receive guidance on tools for continued learning. Designed for beginners, the tutorial aims to foster cross-disciplinary innovation at the intersection of quantum computing and AI.
This tutorial introduces key concepts in Quantum Machine Learning (QML), covering qubits, gates, entanglement, parameterized circuits, and quantum neural networks (QNNs). It highlights recent advances in quantum-enhanced model compression and quantum architecture search (QAS), which improve QML efficiency and scalability. Attendees will gain hands-on experience with QML implementations on quantum simulators and receive guidance on tools for continued learning. Designed for beginners, the tutorial aims to foster cross-disciplinary innovation at the intersection of quantum computing and AI.
This tutorial offers a hands-on introduction into the captivating field of quantum machine learning (QML). Beginning with the bedrock of quantum information science (QIS)-including essential elements like qubits, single and multiple qubit gates, measurements, and entanglement-the session swiftly progresses to foundational QML concepts. Participants will explore parameterized or variational circuits, data encoding or embedding techniques, and quantum circuit design principles. Delving deeper, attendees will examine various QML models, including the quantum support vector machine (QSVM), quantum feed-forward neural network (QNN), and quantum convolutional neural network (QCNN). Pushing boundaries, the tutorial delves into cutting-edge QML models such as quantum recurrent neural networks (QRNN) and quantum reinforcement learning (QRL), alongside privacy-preserving techniques like quantum federated machine learning, bolstered by concrete programming examples. Throughout the tutorial, all topics and concepts are brought to life through practical demonstrations executed on a quantum computer simulator. Designed with novices in mind, the content caters to those eager to embark on their journey into QML. Attendees will also receive guidance on further reading materials, as well as software packages and frameworks to explore beyond the session.
This tutorial covers a hands-on introduction to quantum machine learning. Foundational concepts of quantum information science (QIS) are presented (qubits, single and multiple qubit gates, measurements, and entanglement). Building on that, foundational concepts of quantum machine learning (QML) are introduced (parametrized circuits, data encoding, and feature mapping). Then, QML models are discussed (quantum support vector machine, quantum feedforward neural network, and quantum convolutional neural network). All the aforementioned topics and concepts are examined using codes run on a quantum computer simulator. All the covered materials assume a novice audience interested in learning about QML. Further reading and software packages and frameworks are shared with the audience.
Recent advancements in quantum computing (QC) and machine learning (ML) have fueled significant research efforts aimed at integrating these two transformative technologies. Quantum machine learning (QML), an emerging interdisciplinary field, leverages quantum principles to enhance the performance of ML algorithms. Concurrently, the exploration of systematic and automated approaches for designing high-performance quantum circuit architectures for QML tasks has gained prominence, as these methods empower researchers outside the quantum computing domain to effectively utilize quantum-enhanced tools. This tutorial will provide an in-depth overview of recent breakthroughs in both areas, highlighting their potential to expand the application landscape of QML across diverse fields.
This tutorial intends to introduce readers with a background in AI to quantum machine learning (QML) -- a rapidly evolving field that seeks to leverage the power of quantum computers to reshape the landscape of machine learning. For self-consistency, this tutorial covers foundational principles, representative QML algorithms, their potential applications, and critical aspects such as trainability, generalization, and computational complexity. In addition, practical code demonstrations are provided in https://qml-tutorial.github.io/ to illustrate real-world implementations and facilitate hands-on learning. Together, these elements offer readers a comprehensive overview of the latest advancements in QML. By bridging the gap between classical machine learning and quantum computing, this tutorial serves as a valuable resource for those looking to engage with QML and explore the forefront of AI in the quantum era.
Quantum-enhanced machine learning (QML) is transforming artificial intelligence through the application of quantum computing concepts to solving computationally challenging problems more effectively than conventional methods. By leveraging quantum superposition, entanglement, and parallelism, QML has the capability to speed up deep learning model training, solve combinatorial optimization problems, and improve feature selection in high-dimensional space. It covers basic quantum computer concepts employed within AI, for example, quantum circuits, quantum variational algorithms, and kernel quantum methods, and their impacts on neural networks, generative models, and reinforcement learning. It further refers to the hybrid quantum-classical architectures in AI where a combination of quantum subroutines and classical deep learning models are employed together with the purpose to gain computational speedup in optimization and handling massive data. Despite the transformative promise of quantum AI, technical issues of qubit noise, error correction, and scaling hardware continue to hold back full implementation. This contribution offers a qualitative overview of quantum-enhanced AI, surveying current applications, research endeavors, and upcoming innovation in quantum deep learning, autonomous systems, and scientific computing. The results open the door for large-scale quantum machine learning architectures, which provide new solutions to future uses of AI in finance, medicine, cyber security, and robotics.
Abstract Quantum Machine Learning (QML) is an emerging interdisciplinary field that merges quantum computing with classical machine learning (ML) to enhance computational efficiency, scalability, and accuracy in data-driven tasks. By leveraging quantum properties such as superposition, entanglement, and quantum parallelism, QML has the potential to solve complex problems that are intractable for classical models. This survey provides a comprehensive, systematic review of recent advancements in QML, conducted following the PRISMA 2020 guidelines and covering fundamental encoding techniques that enable quantum computers to process classical data, as well as essential tools, datasets, and evaluation metrics used in quantum model development. Furthermore, it explores various QML approaches, including supervised, semi-supervised, unsupervised, and reinforcement learning, alongside quantum deep learning (QDL) models such as Quantum Neural Networks (QNNs) and Variational Quantum Circuits (VQCs). The paper also discusses the challenges in QML, including hardware limitations, scalability issues, and the need for improved quantum error correction. A dual-axis taxonomy simultaneously classifies algorithms by learning paradigm and quantum-classical integration level – a structure not found in prior surveys. The survey also covers Quantum Transfer Learning, Quantum Graph Neural Networks, and hardware-aware encoding selection, and introduces the first structured adversarial robustness taxonomy and Explainable QML treatment in a comprehensive QML survey. Together, these contributions position this work as both a reference and a methodological guide for advancing QML research and applications.