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

arXiv:2009.13264 · Communications in computer and information science

A Derivative-Free Method for Quantum Perceptron Training in Multi-layered Neural Networks

Tariq Mahmood Khan, Antonio Robles‐Kelly

Published Jan 1, 2020• 14 citations
arXivHTMLPDF
DOI
10.1007/978-3-030-63823-8_29

Related papers

QTN-MLP: Quantum Tensor Network-enhanced MLP for Medical Image Classification

Geng Zhang, Hong Lai

Recently, there has been growing interest in medical image analysis methods based on multi-layer perceptron (MLP), which have demonstrated remarkable performance in this field. Typically, the MLP has been employed to flatten feature maps along the channel and spatial dimensions and encode them to capture the overall feature information. However, for MLP-based architecture, the whole learning process requires high computational complexity, a large number of parameters, and large-scale training datasets. Meanwhile, quantum tensor network (QTN), derived from quantum many-body systems, have gained popularity in machine learning due to their ability to reduce the number of parameters and explore the correlation of remote elements in an image through a tensor contraction operation. In this paper, we propose a novel framework named QTN-MLP based on QTN and MLP to tackle the weaknesses of MLP. This paper has been extensively validated on the COVID-CT dataset and ISIC 2018 dataset, and the experiments show that our method competes with state-of-the-art methods with lower computational complexity and fewer parameters.

International Conference on Computer Supported Cooperative Work in Design (CSCWD)•May 8, 2024•1 citation

A Variational Algorithm for Quantum Single Layer Perceptron

Antonio Macaluso, Filippo Orazi, Matthias Klusch +2 more

Lecture notes in computer science•Jan 1, 2023•8 citations

Parallel Hybrid Networks: An Interplay between Quantum and Classical Neural Networks

Mohammad Kordzanganeh, Daria Kosichkina, Alexey A. Melnikov

The use of quantum neural networks for machine learning is a paradigm that has recently attracted considerable interest. Under certain conditions, these models approximate the distributions of their datasets using truncated Fourier series. Owing to the trigonometric nature of this fit, angle-embedded quantum neural networks may have difficulty fitting nonharmonic features in a given dataset. Moreover, the interpretability of hybrid neural networks remains a challenge. In this study, we introduce an interpretable class of hybrid quantum neural networks that pass the inputs of the dataset in parallel to (a) a classical multi-layered perceptron and (b) a variational quantum circuit, after which the 2 outputs are linearly combined. The quantum neural network creates a smooth sinusoidal foundation based on the training set, and the classical perceptrons fill the nonharmonic gaps in the landscape. We demonstrate this claim using 2 synthetic datasets sampled from periodic distributions with added protrusions as noise. The training results indicate that parallel hybrid network architecture can improve solution optimality on periodic datasets with additional noise.

arXiv:2303.03227•Intelligent Computing•Jan 1, 2023•33 citations

New directions in quantum neural networks research

Wei Cui, Shilu Yan

Control Theory and Technology•Nov 1, 2019•1 citation

Quantum Neural Networks: From Concept to Simulation

Nasrullah Masud, Abdus Sobhan, Md Tanvir Islam Sourav +1 more

Information systems engineering and management•Jan 1, 2025•2 citations

Quantum-Classical Neural Networks: A Hybrid Approach to MNIST Classification

Tur Mohammad Mubtasim, Md. Siam Uddin Molla Antor, Sheikh Shifat

The combination of the principles of quantum computing and classical deep learning is a potentially fruitful direction to develop the field of artificial intelligence, but the benchmarking of such hybrid architectures against standard computer vision problems is an under-explored area. The paper explores the behavior of Hybrid Quantum-Classical Neural Network (HQNN) in the classification of images into multiple classes using the MNIST database. Our architecture is an HQNN implementing an 8-qubit and 2-layer variational circuit, and it is parameterized by a classical multi-layer perceptron (MLP). To make the evaluation process rigorous and fair, the hybrid was benchmarked on a purely classical MLP, which had almost the same parameter footprint ( 105,000 parameters). Results over 50 training epochs show that the classical MLP reached its highest test accuracy of 96.50% and Macro F1 of 0.96. The HQNN was able to converge and learn the data of high dimensions delivering a competitive but slightly lower maximum accuracy of 94.35% and Macro F1 of 0.94. Moreover, there was a high computational cost on the simulation of the quantum layers, which increased the training time by 233 times the classical baseline. These results suggest that while the quantum layer is expressive and capable of learning complex representations, the current state of quantum simulation on classical hardware is a significant bottleneck. Which can be reduced by QPU/NISQ hardware, lighter quantum circuits and better dta encoding.

International Conference on Power, Electronics, Communications, Computing, and Intelligent Infrastructure (PECCII)•Jun 1, 2026•0 citations
Recently, there has been growing interest in medical image analysis methods based on multi-layer perceptron (MLP), which have demonstrated remarkable performance in this field. Typically, the MLP has been employed to flatten feature maps along the channel and spatial dimensions and encode them to capture the overall feature information. However, for MLP-based architecture, the whole learning process requires high computational complexity, a large number of parameters, and large-scale training datasets. Meanwhile, quantum tensor network (QTN), derived from quantum many-body systems, have gained popularity in machine learning due to their ability to reduce the number of parameters and explore the correlation of remote elements in an image through a tensor contraction operation. In this paper, we propose a novel framework named QTN-MLP based on QTN and MLP to tackle the weaknesses of MLP. This paper has been extensively validated on the COVID-CT dataset and ISIC 2018 dataset, and the experiments show that our method competes with state-of-the-art methods with lower computational complexity and fewer parameters.
The use of quantum neural networks for machine learning is a paradigm that has recently attracted considerable interest. Under certain conditions, these models approximate the distributions of their datasets using truncated Fourier series. Owing to the trigonometric nature of this fit, angle-embedded quantum neural networks may have difficulty fitting nonharmonic features in a given dataset. Moreover, the interpretability of hybrid neural networks remains a challenge. In this study, we introduce an interpretable class of hybrid quantum neural networks that pass the inputs of the dataset in parallel to (a) a classical multi-layered perceptron and (b) a variational quantum circuit, after which the 2 outputs are linearly combined. The quantum neural network creates a smooth sinusoidal foundation based on the training set, and the classical perceptrons fill the nonharmonic gaps in the landscape. We demonstrate this claim using 2 synthetic datasets sampled from periodic distributions with added protrusions as noise. The training results indicate that parallel hybrid network architecture can improve solution optimality on periodic datasets with additional noise.
The combination of the principles of quantum computing and classical deep learning is a potentially fruitful direction to develop the field of artificial intelligence, but the benchmarking of such hybrid architectures against standard computer vision problems is an under-explored area. The paper explores the behavior of Hybrid Quantum-Classical Neural Network (HQNN) in the classification of images into multiple classes using the MNIST database. Our architecture is an HQNN implementing an 8-qubit and 2-layer variational circuit, and it is parameterized by a classical multi-layer perceptron (MLP). To make the evaluation process rigorous and fair, the hybrid was benchmarked on a purely classical MLP, which had almost the same parameter footprint ( 105,000 parameters). Results over 50 training epochs show that the classical MLP reached its highest test accuracy of 96.50% and Macro F1 of 0.96. The HQNN was able to converge and learn the data of high dimensions delivering a competitive but slightly lower maximum accuracy of 94.35% and Macro F1 of 0.94. Moreover, there was a high computational cost on the simulation of the quantum layers, which increased the training time by 233 times the classical baseline. These results suggest that while the quantum layer is expressive and capable of learning complex representations, the current state of quantum simulation on classical hardware is a significant bottleneck. Which can be reduced by QPU/NISQ hardware, lighter quantum circuits and better dta encoding.