Evolving Hybrid Quantum-Classical Architectures for Image Classification

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× 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.

HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
Xinghang Yu, Bin Yang
arXiv19 Oct 2026PreprintarXiv licenceFull textInstrumentation & methods Quantum physics & quantum informationarXiv
Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification
Yan-Yan Hou, Jian Li, Chongqiang Ye +3
arXiv14 Sep 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
Divide et Impera quantum neural networks for modular hybrid computing architectures
Emanuele Casciaro, Fabio Mascherpa, Alfonso Amendola +1
arXiv7 Oct 2026PreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv
Self-regulated emergence of heavy-tailed weight distributions in evolving complex network architectures
Jia Li, Cees van Leeuwen, Roman Bauer +1
Communications Biology12 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textStatistical & nonlinear physicsCrossref
Exact diffusion coefficients for quantum--classical hybrid walks
Cook Hyun Kim, Jaesub Park, Namshik Han
arXiv20 Sep 2026PreprintCC BY 4.0Full textQuantum physics & quantum information Statistical & nonlinear physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{kar2026evolving,
  title = {{Evolving Hybrid Quantum-Classical Architectures for Image Classification}},
  author = {Devroop Kar and Daniel Krutz and Travis Desell},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.03220},
  eprint = {2610.03220},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.03220},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Evolving Hybrid Quantum-Classical Architectures for Image Classification
AU  - Devroop Kar
AU  - Daniel Krutz
AU  - Travis Desell
PY  - 2026
DA  - 2026/10/09
PB  - arXiv
DO  - 10.48550/arxiv.2610.03220
UR  - https://arxiv.org/abs/2610.03220
AB  - 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× 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.
ER  -

Abstract

Related

Cite