Quantum machine learning (QML) merges concepts from quantum computing and machine learning. Researchers are actively investigating how quantum computers can enhance machine learning tasks. To support this frontier, numerous open-source projects on GitHub provide learning resources, examples, and code, simplifying the understanding of QML fundamentals and its rapid evolution. This article highlights five particularly valuable GitHub repositories for learning quantum machine learning and tracking its current progress.
1. Mapping the Field: awesome-quantum-machine-learning (⭐ 3.2k)
This extensive list functions as a comprehensive "table of contents" for the QML domain, covering basics, algorithms, study materials, and various libraries or software. It serves as an excellent starting point for beginners, consolidating subtopics like kernels, variational circuits, and hardware limits. Licensed under CC0-1.0, it’s a foundational resource for anyone embarking on quantum machine learning.
2. Exploring Research: awesome-quantum-ml (⭐ 407)
A more focused list, awesome-quantum-ml curates high-quality scientific papers and key resources on machine learning algorithms designed for quantum devices. It's ideal for those with a foundational understanding looking for a queue of papers, surveys, and academic works explaining core concepts, recent findings, and emerging trends in applying quantum computing methods to ML problems. The project also welcomes community contributions via pull requests.
3. Learning by Doing: Hands-On-Quantum-Machine-Learning-With-Python-Vol-1 (⭐ 163)
This repository contains the code for the book "Hands-On Quantum Machine Learning With Python (Vol 1)." Structured as a learning path, it enables users to follow chapters, run experiments, and adjust parameters to observe system behaviors. It is perfectly suited for learners who prefer a practical approach using Python notebooks and scripts.
4. Implementing Projects: Quantum-Machine-Learning-on-Near-Term-Quantum-Devices (⭐ 25)
Though a smaller repository, this resource is highly practical. It features projects specifically designed for near-term quantum devices—today’s noisy and limited qubit hardware. Examples include quantum support vector machines, quantum convolutional neural networks, and data re-uploading models for classification. It effectively illustrates QML operations under real-world hardware constraints.
5. Building Pipelines: qiskit-machine-learning (⭐ 939)
This is a full-featured Qiskit library providing quantum kernels, quantum neural networks, classifiers, and regressors. It integrates seamlessly with PyTorch via the TorchConnector. As a component of the broader Qiskit ecosystem, it is co-maintained by IBM and the Hartree Centre, which is part of the Science and Technology Facilities Council.