Automated quantum circuits improve image classification with fewer parameters
Evolving Hybrid Quantum-Classical Architectures for Image Classification
Neural and Evolutionary ComputingArtificial IntelligenceComputer Vision and Pattern RecognitionMachine Learning
Summary
Quantum computers can work alongside classical computers to help recognize images, but deciding how to build the quantum part is tricky and often done by hand. The authors extended a system that evolves quantum circuits automatically to find better designs for image classification tasks. Their approach created small, task-specific quantum circuits that matched classical methods’ accuracy while using far fewer parameters, especially on popular image datasets like MNIST and CIFAR-10. They also found that the way data is encoded into the quantum circuits makes a big difference in performance.
What this means in practice
- •For quantum machine learning engineers: Design compact quantum circuits as plug-in modules to improve classical image classifiers with fewer parameters and maintain accuracy.
- •For computer vision developers: Integrate evolved quantum circuits with classical feature extractors to build efficient hybrid models for image recognition tasks.
Authors
Devroop Kar, Daniel Krutz, Travis Desell
Abstract
Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum circuit architecture, a choice that remains largely manual. Most existing approaches rely on hand-designed or fixed circuit ansätze, requiring circuit structure, gate composition, and qubit connectivity to be specified in advance with no guarantee that they suit the task. This limitation is especially acute in image classification, where quantum circuits must transform features extracted by classical networks while remaining compact enough for practical training, requirements that generic, task-agnostic ansätze are unlikely to satisfy simultaneously. We extend EXAQC, an evolutionary framework for automated quantum circuit discovery, to image classification. EXAQC evolves PQCs as intermediate processing modules while retaining classical feature-extraction and prediction layers. On MNIST, Fashion-MNIST, and CIFAR-10, EXAQC achieves 98.42%, 90.62%, and 85.47% accuracy, respectively, while using comparable gate counts to other quantum architecture-search methods. Against classical networks, evolved hybrid models maintain comparable accuracy with substantially fewer trainable parameters, reaching 85.68% on CIFAR-10 with over 25$\times$ fewer parameters than a 10-layer CNN. Encoding choice also matters: rotation-based encodings (RX, RY, U3) outperform amplitude encoding by 22-25 points on CIFAR-10. These results demonstrate that automated circuit discovery yields compact quantum modules that can replace larger classical components in vision architectures while retaining competitive accuracy.