# A Quantum of Learning: Using Quaternion Algebra to Model Learning on Quantum Devices

arXiv: https://arxiv.org/abs/2504.13232 · HTML: https://mlsanity.com/paper/2504.13232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Quantum Machine Learning](https://mlsanity.com/paper/1611.09347/) (2016)
- [Efficient Learning for Deep Quantum Neural Networks](https://mlsanity.com/paper/1902.10445/) (2019)
- [Quantum Computing: Lecture Notes](https://mlsanity.com/paper/1907.09415/) (2019)
- [The HR-Calculus: Enabling Information Processing with Quaternion Algebra](https://mlsanity.com/paper/2311.16771/) (2023)
- [Quantum computing through the lens of control: A tutorial introduction](https://mlsanity.com/paper/2310.12571/) (2023)

## Abstract (arXiv)

This article considers the problem of designing adaption and optimisation techniques for training quantum learning machines. To this end, the division algebra of quaternions is used to derive an effective model for representing computation and measurement operations on qubits. In turn, the derived model, serves as the foundation for formulating an adaptive learning problem on principal quantum learning units, thereby establishing quantum information processing units akin to that of neurons in classical approaches. Then, leveraging the modern HR-calculus, a comprehensive training framework for learning on quantum machines is developed. The quaternion-valued model accommodates mathematical tractability and establishment of performance criteria, such as convergence conditions.