ResQ: A Novel Framework to Implement Residual Neural Networks on Analog Rydberg Atom Quantum Computers

TL;DR

This paper introduces ResQ, a framework leveraging analog Rydberg atom quantum computers to implement residual neural networks via neural ODEs, aiming to enhance quantum machine learning capabilities.

Contribution

The paper presents ResQ, a novel framework that optimizes Rydberg atom quantum computers for neural ODE-based residual neural networks in quantum machine learning.

Findings

Analog Rydberg atom quantum computers are well-suited for ResNets.

ResQ enables efficient implementation of neural ODEs on quantum hardware.

Potential for accelerated quantum machine learning applications.

Abstract

Research in quantum machine learning has recently proliferated due to the potential of quantum computing to accelerate machine learning. An area of machine learning that has not yet been explored is neural ordinary differential equation (neural ODE) based residual neural networks (ResNets), which aim to improve the effectiveness of neural networks using the principles of ordinary differential equations. In this work, we present our insights about why analog Rydberg atom quantum computers are especially well-suited for ResNets. We also introduce ResQ, a novel framework to optimize the dynamics of Rydberg atom quantum computers to solve classification problems in machine learning using analog quantum neural ODEs.