Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Machine Intelligence

Quantum transformers for image classification: integrating variational quantum circuits and quantum wavelet KAN

Zihan Geng, Xinghua Wang, Xiaoran Li, Feng Zhang

Published Apr 13, 2026• 1 citation
Publisher
DOI
10.1007/s42484-026-00381-w

Related papers

Hybrid Variational Quantum Circuit for Satellite Image Classification

Trung Thanh Pham, Loc X. Nguyen, Phuong-Nam Tran +2 more

International Conference on Information Networking•Jan 14, 2026•0 citations

Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks

Jiun-Cheng Jiang, Morris Yu-Chao Huang, Tianlong Chen +1 more

Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions. We unify these directions by introducing the quantum variational activation function (QVAF), a general framework in which parameterized quantum circuits serve as learnable activation functions; in this work we study an efficient single-qubit instantiation called DatA Re-Uploading ActivatioN (DARUAN). We show that DARUAN with trainable data-preprocessing weights can realize an exponentially growing accessible frequency support with the number of re-uploading repetitions; for an explicit geometric choice of these weights, this gives a capacity-level exponential parameter reduction relative to independently parameterized Fourier activations. Embedding DARUAN into KAN yields the quantum-inspired Kolmogorov-Arnold Network (QKAN), which retains the interpretability of the KAN architecture while improving parameter efficiency, expressivity, and generalization. We further introduce layer extension and the hybrid QKAN (HQKAN) architecture to improve scalability and computational efficiency, enabling QKAN modules to act as compact replacements for multi-layer perceptrons (MLPs) in large-scale models. We provide theoretical analysis and extensive experiments on function regression, image classification, and autoregressive generative language modeling, demonstrating the efficiency and scalability of QKANs. Because the single-qubit circuits are efficiently simulable on classical quantum simulators, QKANs have quantum-inspired advantage in parameter efficiency and training stability; DARUANs and QKANs serve as present-day validation of the QVAF concept, and the trained DARUANs are directly executable and feasible on current noisy intermediate-scale quantum (NISQ) hardware for inference validation.

arXiv:2509.14026•Sep 17, 2025•14 citations

Neural Networks with Variational Quantum Circuits

Syed Muhammad Abuzar Rizvi, Muhammad Shohibul Ulum, Naema Asif +1 more

Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering•Jan 1, 2023•10 citations

VQ‐Rice: Integrating Variational Quantum Models for Intelligent Rice Disease Classification

Daya Shankar Verma, Jitendra Kumar Mishra, Ankit Kumar +2 more

This study presents a novel hybrid quantum‐classical framework for rice disease diagnosis, leveraging variational quantum circuits (VQCs) to address the limitations of traditional and deep learning models in precision agriculture. The proposed Quantum Variational Rice Disease Network (QVRDN) integrates quantum feature encoding, variational quantum processing, and adaptive optimization to achieve superior classification accuracy, efficiency, and robustness. Using a curated dataset of 3000 annotated rice leaf images spanning major disease categories, the QVRDN framework applies dimensionality reduction and quantum angle encoding to transform the image features into quantum states, which are then processed by parameterized quantum circuits for disease classification. Experimental results demonstrate that QVRDN outperforms classical models, including SVM, random forest, CNN, and ResNet50‐achieving, the highest accuracy of 97.8%, faster inference times, and greater resilience to noise and limited data. The compact design of the framework enables edge deployment without GPU dependency, making it suitable for resource‐constrained agricultural environments. By demonstrating the feasibility and advantages of quantum machine learning in crop health monitoring, this study establishes a foundation for quantum‐enhanced, data‐efficient agricultural diagnostics and paves the way for future advances in intelligent, field‐ready quantum geoinformatics systems.

International Journal of Intelligent Systems•Jan 1, 2025•4 citations

Variational Techniques for Quantum Neural Network Architectures: A Survey

Bhagaban Swain, Sudipta Roy

Science & Technology Journal•Jan 1, 2024•0 citations

A Generalised Transform Methodology Using Quantum Computation and Its Application for Electrocardiogram (ECG) Classification

Bidisha Dhara, Monika Agrawal, Sumantra Dutta Roy

ABSTRACT Transforms play a pivotal role in the study of signals and images. With the advent of quantum systems, analysing signals in the quantum domain is of particular interest. In this work, we aim to build a generalised transform circuit in the quantum domain. We have shown the working of this circuit for Wavelet transform, Fourier transform, and Discrete Cosine Transform (DCT) on vector, matrix, and an image respectively. We also take inverse transforms in each of the cases to match with the given initial input. We use simulators for this work, and the results obtained are favourable. We further use this circuit for classification of heart beats as it is an essential task in detection of cardiac diseases. We utilise both classical and quantum computation to classify beats of Electrocardiogram (ECG, hereafter) signals into normal and not‐normal beats (non‐beats and abnormal beats). This novel architecture to carry out transform is quite general and can be used for any arbitrary transform.

IET Quantum Communication•Jan 1, 2025•4 citations
Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions. We unify these directions by introducing the quantum variational activation function (QVAF), a general framework in which parameterized quantum circuits serve as learnable activation functions; in this work we study an efficient single-qubit instantiation called DatA Re-Uploading ActivatioN (DARUAN). We show that DARUAN with trainable data-preprocessing weights can realize an exponentially growing accessible frequency support with the number of re-uploading repetitions; for an explicit geometric choice of these weights, this gives a capacity-level exponential parameter reduction relative to independently parameterized Fourier activations. Embedding DARUAN into KAN yields the quantum-inspired Kolmogorov-Arnold Network (QKAN), which retains the interpretability of the KAN architecture while improving parameter efficiency, expressivity, and generalization. We further introduce layer extension and the hybrid QKAN (HQKAN) architecture to improve scalability and computational efficiency, enabling QKAN modules to act as compact replacements for multi-layer perceptrons (MLPs) in large-scale models. We provide theoretical analysis and extensive experiments on function regression, image classification, and autoregressive generative language modeling, demonstrating the efficiency and scalability of QKANs. Because the single-qubit circuits are efficiently simulable on classical quantum simulators, QKANs have quantum-inspired advantage in parameter efficiency and training stability; DARUANs and QKANs serve as present-day validation of the QVAF concept, and the trained DARUANs are directly executable and feasible on current noisy intermediate-scale quantum (NISQ) hardware for inference validation.
This study presents a novel hybrid quantum‐classical framework for rice disease diagnosis, leveraging variational quantum circuits (VQCs) to address the limitations of traditional and deep learning models in precision agriculture. The proposed Quantum Variational Rice Disease Network (QVRDN) integrates quantum feature encoding, variational quantum processing, and adaptive optimization to achieve superior classification accuracy, efficiency, and robustness. Using a curated dataset of 3000 annotated rice leaf images spanning major disease categories, the QVRDN framework applies dimensionality reduction and quantum angle encoding to transform the image features into quantum states, which are then processed by parameterized quantum circuits for disease classification. Experimental results demonstrate that QVRDN outperforms classical models, including SVM, random forest, CNN, and ResNet50‐achieving, the highest accuracy of 97.8%, faster inference times, and greater resilience to noise and limited data. The compact design of the framework enables edge deployment without GPU dependency, making it suitable for resource‐constrained agricultural environments. By demonstrating the feasibility and advantages of quantum machine learning in crop health monitoring, this study establishes a foundation for quantum‐enhanced, data‐efficient agricultural diagnostics and paves the way for future advances in intelligent, field‐ready quantum geoinformatics systems.
ABSTRACT Transforms play a pivotal role in the study of signals and images. With the advent of quantum systems, analysing signals in the quantum domain is of particular interest. In this work, we aim to build a generalised transform circuit in the quantum domain. We have shown the working of this circuit for Wavelet transform, Fourier transform, and Discrete Cosine Transform (DCT) on vector, matrix, and an image respectively. We also take inverse transforms in each of the cases to match with the given initial input. We use simulators for this work, and the results obtained are favourable. We further use this circuit for classification of heart beats as it is an essential task in detection of cardiac diseases. We utilise both classical and quantum computation to classify beats of Electrocardiogram (ECG, hereafter) signals into normal and not‐normal beats (non‐beats and abnormal beats). This novel architecture to carry out transform is quite general and can be used for any arbitrary transform.