Skip to main content

Research Repository

Advanced Search

Training neural networks with universal adiabatic quantum computing

Abel, Steve; Criado, Juan Carlos; Spannowsky, Michael

Training neural networks with universal adiabatic quantum computing Thumbnail


Authors

Juan Carlos Criado



Abstract

The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This article presents a novel approach to NN training using adiabatic quantum computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimization problems. We propose a universal AQC method that can be implemented on gate quantum computers, allowing for a broad range of Hamiltonians and thus enabling the training of expressive neural networks. We apply this approach to various neural networks with continuous, discrete, and binary weights. The study results indicate that AQC can very efficiently evaluate the global minimum of the loss function, offering a promising alternative to classical training methods.

Citation

Abel, S., Criado, J. C., & Spannowsky, M. (2024). Training neural networks with universal adiabatic quantum computing. Frontiers in Artificial Intelligence, 7, Article 1368569. https://doi.org/10.3389/frai.2024.1368569

Journal Article Type Article
Acceptance Date May 27, 2024
Online Publication Date Jun 21, 2024
Publication Date Jun 21, 2024
Deposit Date Jul 24, 2024
Publicly Available Date Jul 24, 2024
Journal Frontiers in Artificial Intelligence
Print ISSN 2624-8212
Electronic ISSN 2624-8212
Publisher Frontiers Media
Peer Reviewed Peer Reviewed
Volume 7
Article Number 1368569
DOI https://doi.org/10.3389/frai.2024.1368569
Keywords binary neural networks, adiabatic quantum computing, neural networks, quantum computing, NN training
Public URL https://durham-repository.worktribe.com/output/2520549

Files





You might also like



Downloadable Citations