An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks

Recent advancements in quantum machine learning have spurred the development of hybrid quantum-classical convolutional neural networks (HQCCNNs), which have demonstrated promising potential for image classification tasks. Building on the operational principles of classical transposed convolutional n...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Hai, Chen Liang, Hao Yaming, Yu Wenli, Shi Fengquan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10891464/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849744472402821120
author Li Hai
Chen Liang
Hao Yaming
Yu Wenli
Shi Fengquan
author_facet Li Hai
Chen Liang
Hao Yaming
Yu Wenli
Shi Fengquan
author_sort Li Hai
collection DOAJ
description Recent advancements in quantum machine learning have spurred the development of hybrid quantum-classical convolutional neural networks (HQCCNNs), which have demonstrated promising potential for image classification tasks. Building on the operational principles of classical transposed convolutional neural networks (CNNs), we introduce a novel quantum variant: the Quantum Pseudo-Transposed Convolutional Neural Network (QPTCNN). The QPTCNN adapts the concept of classical transposed CNNs to the quantum domain, leveraging a hybrid quantum-classical framework that combines a quantum convolutional layer with a classical fully connected layer. In the QPTCNN, the quantum convolutional layer emulates a transposed convolution operation, ensuring that the output feature map retains the same dimensions as the input image. This is accomplished using rotational angle encoding and a ring-structured quantum circuit, interconnected by two-qubit control gates such as CNOT and CRY gates, facilitating efficient quantum convolution. We evaluated the performance of the QPTCNN on the MNIST and Fashion-MNIST datasets, with two distinct versions of the model: Model A, which utilizes a CNOT-gate entanglement circuit, and Model B, which employs a CRY-gate entanglement circuit. The results demonstrate that both Model A and Model B achieve strong performance across the datasets. However, Model A outperforms Model B, achieving higher classification accuracy and lower loss compared to earlier models. These findings suggest that the QPTCNN is highly capable of learning and extracting relevant feature information from input images, making it well-suited for high-performance image classification tasks. This work represents a significant advancement in quantum-enhanced image classification.
format Article
id doaj-art-8271b3bbf0e648069a9f2d6c068c2eb8
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8271b3bbf0e648069a9f2d6c068c2eb82025-08-20T03:15:47ZengIEEEIEEE Access2169-35362025-01-0113371083711710.1109/ACCESS.2025.354316410891464An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural NetworksLi Hai0https://orcid.org/0000-0001-6577-2050Chen Liang1Hao Yaming2Yu Wenli3Shi Fengquan4School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, ChinaRecent advancements in quantum machine learning have spurred the development of hybrid quantum-classical convolutional neural networks (HQCCNNs), which have demonstrated promising potential for image classification tasks. Building on the operational principles of classical transposed convolutional neural networks (CNNs), we introduce a novel quantum variant: the Quantum Pseudo-Transposed Convolutional Neural Network (QPTCNN). The QPTCNN adapts the concept of classical transposed CNNs to the quantum domain, leveraging a hybrid quantum-classical framework that combines a quantum convolutional layer with a classical fully connected layer. In the QPTCNN, the quantum convolutional layer emulates a transposed convolution operation, ensuring that the output feature map retains the same dimensions as the input image. This is accomplished using rotational angle encoding and a ring-structured quantum circuit, interconnected by two-qubit control gates such as CNOT and CRY gates, facilitating efficient quantum convolution. We evaluated the performance of the QPTCNN on the MNIST and Fashion-MNIST datasets, with two distinct versions of the model: Model A, which utilizes a CNOT-gate entanglement circuit, and Model B, which employs a CRY-gate entanglement circuit. The results demonstrate that both Model A and Model B achieve strong performance across the datasets. However, Model A outperforms Model B, achieving higher classification accuracy and lower loss compared to earlier models. These findings suggest that the QPTCNN is highly capable of learning and extracting relevant feature information from input images, making it well-suited for high-performance image classification tasks. This work represents a significant advancement in quantum-enhanced image classification.https://ieeexplore.ieee.org/document/10891464/Convolutional neural networksquantum pseudo-transposed convolutional neural networksquantum circuitstransposed convolution
spellingShingle Li Hai
Chen Liang
Hao Yaming
Yu Wenli
Shi Fengquan
An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
IEEE Access
Convolutional neural networks
quantum pseudo-transposed convolutional neural networks
quantum circuits
transposed convolution
title An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
title_full An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
title_fullStr An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
title_full_unstemmed An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
title_short An Improved Convolutional Neural Networks: Quantum Pseudo-Transposed Convolutional Neural Networks
title_sort improved convolutional neural networks quantum pseudo transposed convolutional neural networks
topic Convolutional neural networks
quantum pseudo-transposed convolutional neural networks
quantum circuits
transposed convolution
url https://ieeexplore.ieee.org/document/10891464/
work_keys_str_mv AT lihai animprovedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT chenliang animprovedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT haoyaming animprovedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT yuwenli animprovedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT shifengquan animprovedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT lihai improvedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT chenliang improvedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT haoyaming improvedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT yuwenli improvedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks
AT shifengquan improvedconvolutionalneuralnetworksquantumpseudotransposedconvolutionalneuralnetworks