26th Australian Institute of Physics Congress and the Australian and New Zealand Conference on Optics and Photonics

A hardware efficient quantum residual neural network without post-selection

Not scheduled

20m

Belinda Hutchinson Building (The University of Sydney )

Contributed Oral AIP | Quantum Science and Technology (QST)

Speaker

Akib Karim (CSIRO)

Description

We propose a hardware efficient quantum residual neural network that implements non-unitary operations using ancilla qubits to allow for the same expressivity but significantly lower depth than traditional unitary quantum machine learning. In contrast to previous implementations of residual connections, our architecture avoids post-selection to ensure minimal measurement overhead. 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 as well as exploring non-unitarity for quantum machine learning.