# Training Neural Networks with Universal Adiabatic Quantum Computing

arXiv: https://arxiv.org/abs/2308.13028 · HTML: https://mlsanity.com/paper/2308.13028/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 24 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [Regularizing Activation Distribution for Training Binarized Deep Networks](https://mlsanity.com/paper/1904.02823/) (2019)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Qibo: a framework for quantum simulation with hardware acceleration](https://mlsanity.com/paper/2009.01845/) (2020)
- [Quantum Optimisation of Complex Systems with a Quantum Annealer](https://mlsanity.com/paper/2105.13945/) (2021)
- [Completely Quantum Neural Networks](https://mlsanity.com/paper/2202.11727/) (2022)
- [Qade: Solving Differential Equations on Quantum Annealers](https://mlsanity.com/paper/2204.03657/) (2022)

## Built on by (most cited first, 1 of 1)

- [QUBO-based training for VQAs on Quantum Annealers](https://mlsanity.com/paper/2509.01821/) (2025)

## Abstract (arXiv)

The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This paper presents a novel approach to NN training using Adiabatic Quantum Computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimisation 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. Our results indicate that AQC can very efficiently find the global minimum of the loss function, offering a promising alternative to classical training methods.