Digital-analog quantum convolutional neural networks for image classification
Physical Review Research · 11.12.2024 · 6 (4)
DOI: 10.1103/physrevresearch.6.l042060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Research, online erschienen am 11.12.2024. Verfasst von Anton Simen und 8 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Valencian Government, Spanish Ministry of Economic Affairs and Digital Transformation.
Abstract (Originalsprache)
We propose digital-analog quantum kernels for enhancing the detection of complex features in the classification of images. We consider multipartite-entangled analog blocks, stemming from native Ising interactions in neutral-atom quantum processors, and individual operations as digital steps to implement the protocol. To further improve the detection of complex features, we apply multiple quantum kernels by varying the qubit connectivity according to the hardware constraints. An architecture that combines nontrainable quantum kernels and standard convolutional neural networks is used to classify realistic medical images, from breast cancer and pneumonia diseases, with a significantly reduced number of parameters. Despite this fact, the model exhibits better performance than its classical counterparts and achieves comparable metrics according to public benchmarks. These findings highlight the potential of digital-analog quantum convolutions in extracting complex and meaningful features from images, positioning them as a candidate model for addressing challenging classification problems. Published by the American Physical Society 2024
Förderung
- Valencian Government
- Spanish Ministry of Economic Affairs and Digital Transformation
Zitieren
APA
Simen, A., Flores-Garrigos, C., Hegade, N. N., Montalban, I., Vives-Gilabert, Y., Michon, E., Zhang, Q., Solano, E., & Martín-Guerrero, J. D. (2024). Digital-analog quantum convolutional neural networks for image classification. Physical Review Research, 6(4). https://doi.org/10.1103/physrevresearch.6.l042060
Vancouver
Simen A, Flores-Garrigos C, Hegade NN, Montalban I, Vives-Gilabert Y, Michon E, et al. Digital-analog quantum convolutional neural networks for image classification. Physical Review Research. 2024;6(4). doi:10.1103/physrevresearch.6.l042060
BibTeX
@article{Simen2024,
author = {Simen, Anton and Flores-Garrigos, Carlos and Hegade, Narendra N. and Montalban, Iraitz and Vives-Gilabert, Yolanda and Michon, Eric and Zhang, Qi and Solano, Enrique and Martín-Guerrero, José D.},
title = {Digital-analog quantum convolutional neural networks for image classification},
journal = {Physical Review Research},
year = {2024},
volume = {6},
number = {4},
doi = {10.1103/physrevresearch.6.l042060}
}
EUVIMED