A hardware efficient quantum residual neural network without post-selection

TL;DR

This paper introduces a hardware-efficient quantum residual neural network that avoids post-selection, reduces gate count, and maintains high accuracy and robustness in image classification tasks.

Contribution

The authors present a novel quantum residual neural network architecture that is hardware-efficient, avoids post-selection, and mitigates barren plateaus, enabling practical quantum machine learning.

Findings

Achieves 99% accuracy on binary classification and 80% on multi-class datasets.

Requires 10x fewer gates than standard variational models.

Demonstrates adversarial robustness in quantum machine learning.

Abstract

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.