Photo by the author
# Introducing quantum machine learning
Quantum machine learning combines ideas from quantum computing and machine learning. Many researchers are exploring how quantum computers can support with machine learning tasks. To support this work, several open source projects on GitHub share learning resources, examples and code. These repositories make it easier to understand the basics and see how the field is developing. In this article, we will look at five repositories that are particularly useful for learning quantum machine learning and understanding current advancements in space. These resources provide different starting points for different learning styles.
# 1. Field mapping
This massive list by amazing-quantum machine learning (⭐ 3.2k) acts as a “table of contents” for the field. It covers fundamentals, algorithms, learning materials, and libraries and software. It’s perfect for beginners who want to see all the subtopics – such as kernels, variational circuits, or hardware limitations – in one place. Licensed under CC0-1.0, it is an indispensable starting point for anyone wanting to learn the fundamentals of quantum machine learning.
# 2. Discovering research
The amazing-quantum-ml (⭐ 407) the list is smaller and more focused on high-quality research articles and key resources on machine learning algorithms running on quantum devices. This is perfect if you already know the basics of the field and want a queue of articles, surveys, and academic papers explaining key concepts, recent discoveries, and emerging trends in applying quantum computing methods to machine learning problems. The project also accepts community contributions via pull requests.
# 3. Learning by doing
Repository Practical-Quantum-Machine-Learning-with-Python-Volume-1 (⭐ 163) contains the book’s code Practical Quantum Machine Learning with Python (Volume 1). It’s structured like a learning path, allowing you to follow chapters, run experiments, and adjust parameters to see how your systems behave. It is perfect for students who prefer to learn by doing Python notebooks and scripts.
# 4. Project implementation
Although this is a smaller repository, Quantum machine learning on quantum devices in the near future (⭐ 25) is very practical. Includes projects focusing on near-term quantum devices – i.e. today’s clamorous and narrow qubit hardware. The repository includes projects such as quantum support vector machines, quantum neural networks, and data re-upload models for classification tasks. It highlights real-world limitations, which is useful for seeing how quantum machine learning performs on current hardware.
# 5. Construction of pipelines
It is fully functional qiskit machine learning (⭐ 939) library containing quantum kernels, quantum neural networks, classifiers and regressors. Integrates with PyTorch via TorchConnector. Within Kiskit an ecosystem that is co-maintained by IBM and Hartree Centrewhich is part of the Science and Technology Facilities Council (STFC). This is ideal if you want to build tough quantum machine learning pipelines, not just research them.
# Developing learning sequences
A productive learning sequence involves starting with one “awesome” space mapping list, using a document-focused list to deepen knowledge, and then alternating between guided notebooks and short-term hands-on projects. Finally, you can apply the Qiskit library as a core set of experimentation tools that can be extended into fully professional workflows.
Kanwal Mehreen is a machine learning engineer and technical writer with a deep passion for data science and the intersection of artificial intelligence and medicine. She is co-author of the e-book “Maximizing Productivity with ChatGPT”. As a 2022 Google Generation Scholar for APAC, she promotes diversity and academic excellence. She is also recognized as a Teradata Diversity in Tech Scholar, a Mitacs Globalink Research Scholar, and a Harvard WeCode Scholar. Kanwal is a staunch advocate for change and founded FEMCodes to empower women in STEM fields.