The fundamentals of quantum neural networks
- Publication Type:
- Thesis
- Issue Date:
- 2024
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Quantum machine learning is the interplay of machine learning with the concepts of quantum computing. Largely a subset of quantum computing research, it aims to improve machine learning algorithms with the use of quantum computers. One of the most prominent techniques within quantum machine learning are quantum neural networks. This thesis advances the field of quantum neural networks with three main contributions. First, we introduce the idea of distributed quantum neural networks, whereby model training takes place in several quantum nodes. In this part, we consider ideas from distributed deep learning as they apply to quantum neural networks. In the second part, we design a quantum-inspired algorithm that introduces a new class of classical probabilistic circuits. Our algorithm is tested on graphs of various sizes, and performs comparably to the algorithm using quantum resources. In the final part, we address model interpretability by generalizing a local model-agnostic interpretability algorithm, and introduce the region of indecision, where data samples receive random labels. Overall, this thesis contributes to the literature of quantum neural networks from diverse avenues, that collectively advance our pursuit of more efficient and interpretable quantum learning models.
Please use this identifier to cite or link to this item: