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

2025-06-26

AI Summary

Quantum machine learning lacks exploration of Neural Ordinary Differential Equation (Neural ODE)-based residual networks (ResNets) on analog quantum hardware. Method: This work establishes, for the first time, a physical isomorphism between Rydberg atom arrays and Neural ODEs in continuous-time dynamics, and proposes ResQ—the first end-to-end quantum ResNet modeling framework tailored for analog Rydberg quantum computers. ResQ leverages the native continuous Hamiltonian evolution of atomic arrays to bypass discretization bottlenecks inherent in gate-based quantum circuits, realizing hardware-native ResNet dynamics via parameterized Hamiltonian design and quantum optimal control. Contribution/Results: On classification tasks, ResQ achieves accuracy comparable to classical ResNets using significantly fewer trainable parameters and training iterations. This demonstrates a scalable, physically realizable paradigm for quantum neural networks grounded in analog quantum simulation.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Implementing residual neural networks on quantum computers
• Exploring neural ODE-based ResNets for quantum machine learning
• Optimizing Rydberg atom dynamics for quantum classification tasks

Innovation

• ResQ framework for analog quantum ResNets
• Rydberg atom quantum computers optimization
• Analog quantum neural ODEs for classification