Quantum Deep Learning: Sampling Neural Nets with a Quantum Annealer

TL;DR

This paper explores using quantum annealers to perform fast sampling in deep neural networks, demonstrating a method to transfer CNNs to quantum hardware and achieve significant speedups in image classification.

Contribution

It introduces a novel approach to implement neural networks on quantum annealers, overcoming key challenges related to model size and binary states.

Findings

Successful transfer of CNNs to quantum annealer

Potential classification speedup of at least tenfold

Feasibility of energy-based models on quantum hardware

Abstract

We demonstrate the feasibility of framing a classically learned deep neural network as an energy based model that can be processed on a one-step quantum annealer in order to exploit fast sampling times. We propose approaches to overcome two hurdles for high resolution image classification on a quantum processing unit (QPU): the required number and binary nature of the model states. With this novel method we successfully transfer a convolutional neural network to the QPU and show the potential for classification speedup of at least one order of magnitude.