Digital-analog quantum convolutional neural networks for image classification
arXiv:2405.00548 · doi:10.1103/PhysRevResearch.6.L042060
Abstract
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 improving the detection of complex features, we apply multiple quantum kernels by varying the qubit connectivity according to the hardware constraints. An architecture that combines non-trainable 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 demonstrate the relevance of digital-analog encoding, paving the way for surpassing classical models in image recognition approaching us to quantum-advantage regimes.
7 pages, 3 figures
References in corpus (15)
- MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
- High-fidelity parallel entangling gates on a neutral atom quantum computer
- Quantum computing with neutral atoms
- Quantum Optimization of Maximum Independent Set using Rydberg Atom Arrays
- Quantum convolutional neural network for classical data classification
- Hybrid quantum convolutional neural networks model for COVID-19 prediction using chest X-Ray images
- Neutral Atom Quantum Computing Hardware: Performance and End-User Perspective
- Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
- Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
- Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
- Synthesis of and compilation with time-optimal multi-qubit gates
- Superconducting Circuit Architecture for Digital-Analog Quantum Computing
- Randomness-enhanced expressivity of quantum neural networks
- Variational generation of spin squeezing on one-dimensional quantum devices with nearest-neighbor interactions
- Digital-analog quantum learning on Rydberg atom arrays