A hardware efficient quantum residual neural network without post-selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khatun, Amena, Karim, Akib, Usman, Muhammad
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917517822263296
author Khatun, Amena
Karim, Akib
Usman, Muhammad
author_facet Khatun, Amena
Karim, Akib
Usman, Muhammad
contents We propose a hardware efficient quantum residual neural network which implements residual connections through a deterministic mixture of the identity operation and variational unitaries, enabling fully differentiable training. In contrast to the previous implementation of residual connections, our architecture avoids post-selection while preserving residual learning. Furthermore, we highlight circuit constructions where barren plateaus could be mitigated, which are considered as a major limitation of variational quantum learning models. In order to show the working of our model, we report its application to image classification tasks by training it for MNIST, CIFAR, and SARFish datasets, achieving accuracies of 99\% and 80\% for binary and multi-class classifications, respectively. These accuracies are comparable to previously achieved from the standard variational models, however our model requires 10x fewer gates making it better suited for resource constraint near-term quantum processors. In addition to high accuracies, the proposed architecture also demonstrates adversarial robustness which is another desirable parameter for quantum machine learning models. Overall our architecture offers a new pathway for developing accurate, robust, trainable and hardware efficient quantum machine learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06866
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A hardware efficient quantum residual neural network without post-selection
Khatun, Amena
Karim, Akib
Usman, Muhammad
Quantum Physics
We propose a hardware efficient quantum residual neural network which implements residual connections through a deterministic mixture of the identity operation and variational unitaries, enabling fully differentiable training. In contrast to the previous implementation of residual connections, our architecture avoids post-selection while preserving residual learning. Furthermore, we highlight circuit constructions where barren plateaus could be mitigated, which are considered as a major limitation of variational quantum learning models. In order to show the working of our model, we report its application to image classification tasks by training it for MNIST, CIFAR, and SARFish datasets, achieving accuracies of 99\% and 80\% for binary and multi-class classifications, respectively. These accuracies are comparable to previously achieved from the standard variational models, however our model requires 10x fewer gates making it better suited for resource constraint near-term quantum processors. In addition to high accuracies, the proposed architecture also demonstrates adversarial robustness which is another desirable parameter for quantum machine learning models. Overall our architecture offers a new pathway for developing accurate, robust, trainable and hardware efficient quantum machine learning models.
title A hardware efficient quantum residual neural network without post-selection
topic Quantum Physics
url https://arxiv.org/abs/2604.06866