IEEE EUROCON - International Conference on Computer as a Tool (EUROCON)

Impact of Hybrid Neural Network Structure on Performance of Multiclass Classification

Yevhenii Trochun, Evgen Pavlov, Sergii Stirenko, Yuri G. Gordienko

Published Jul 6, 2021• 8 citations

Abstract

This article describes hybrid convolutional neural network that uses one quantum circuit for image classification. The different configurations of the hybrid neural network with the quantum circuit are considered. Several different quantum circuits with different number of qubits are compared. These hybrid neural network configurations are evaluated on MNIST and MNIST Fashion datasets, which is radically different from MNIST dataset. Performance of hybrid neural network is compared for multiclass classification on MNIST and MNIST Fashion datasets for 4, 6, 8, 10 classes using quantum circuits with 2, 3, 4 qubits. The results of the experiments indicate the feasibility of using hybrid neural networks for multiclass classification.

DOI: 10.1109/eurocon52738.2021.9535586

Related papers

Hybrid Classic-Quantum Neural Networks for Image Classification

Yevhenii Trochun, Sergii Stirenko, Oleksandr Rokovyi +3 more

In the last decade, quantum computing (QC) has shown its great potential in advancing research in many fields. Here we introduce a new quantum-classical neural network, by combining quantum computing and classical computing in a hybrid neural network (HNN) that can be trained to perform image classification. The HNN on the basis of the classic convolutional neural network (CNN) with quantum circuit is considered for image classification problem. The various configurations of HNN were investigated where QC with different number of qubits were used and compared. The HNN configurations were trained, validated, and tested on the more complex CIFAR10 and CIFAR100 datasets in addition to our previous attempts on the simpler MNIST, notMNIST, MNIST Fashion datasets. Performance of HNN was compared for multiclass classification on these datasets for different number of classes (from 2 to 10) using QCs with correspondent number of qubits (from 2 to 4). The metrics measured (accuracy and loss) during these experiments support our assumption about feasibility of HNN application for multiclass classification problems.

IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)Sep 22, 202121 citations

Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning

Denis Bokhan, Alena S. Mastiukova, Aleksey S. Boev +2 more

Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that the accuracy of our solution is similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our findings will provide a new step toward the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.

arXiv:2203.15368Frontiers in PhysicsNov 23, 202281 citations

Quantum Convolutional Neural Network Architecture for Multi-Class Classification

Samarth Kashyap, Shayan Srinivasa Garani

We propose quantum circuit architectures for convolutional neural networks based on generalized 3-qubit and 2-qubit quantum gates for the multiclass classification problem. The quantum architecture is equivalent to a classical convolutional neural network with fully connected layers and densely connected layers. The quantum circuit parameters are optimized by minimizing the cross-entropy loss function. We validate the classification performance over several model configurations on the MNIST, Fashion-MNIST and Kuzushiji-MNIST datasets. Our proposed architecture shows classification accuracies that are comparable to classical CNNs with a similar number of parameters. In addition to this, we find that circuit depth is greatly decreased by a logarithmic factor compared to classical CNNs. We study the performance and complexity tradeoffs over several model configurations within the proposed quantum CNN architecture.

International Joint Conference on Neural Networks (IJCNN)Jun 18, 20237 citations

Research on image classification using quantum convolutional neural networks based on multiple approaches

Yumin Dong, Xiaofeng Ni, Tonglei Sun +2 more

Abstract With the significant enhancement of quantum computing capabilities and their expanding applications in various fields, quantum image processing combined with quantum computing has become a key area of research in quantum computing, holding important theoretical value. In the face of the challenges posed by the digital information era, image classification technology demands higher standards from machine learning algorithms in terms of accuracy, computational speed, generalization capability, and complexity. This paper studies a series of quantum data encoding methods and parametric quantum circuit architectures, and proposes the application of Hybrid Hierarchical Encoding (HHE) and Hybrid Quantum Convolutional Neural Network (HQCNN). The new encoding method HHE integrates the benefits of angle encoding and enhances the hybrid amplitude encoding design to achieve optimal classification performance without compromising the depth of quantum circuits.HQCNN demonstrates outstanding classification performance and remarkable control over model complexity by leveraging the data processing capabilities of classical convolution and the complex computational power of quantum convolution. Experimental results show that HHE and HQCNN achieve better classification accuracy on the MNIST and Fashion-MNIST datasets compared to traditional classical CNN models, particularly when the number of parameters is significantly reduced.

Physica ScriptaMar 18, 20252 citations

Performance analysis of quantum convolutional layers for image classification

Qiuyu Xiang, Dongfen Li, Yuchen Sun +6 more

Abstract In recent years, with the rapid development of quantum computing technology, the fusion of quantum computing and machine learning techniques is becoming a research hotspot in the field of machine learning. This article aims to explore the impact of the depth and width of quantum convolutional layers on image classification tasks in Quantum−Classical Hybrid Convolutional Neural Networks. To this end, a model combining parameterized quantum circuits and classical neural networks is designed, and a series of experiments are conducted on the MNIST dataset to assess the specific effects of different configurations of quantum convolutional layers on model performance. The research results indicate that simply increasing the depth or width of quantum convolutional layers does not guarantee performance improvement and sometimes may even lead to performance degradation. Therefore, when designing quantum convolutional layers, we should make reasonable choices based on the actual needs of the application scenarios. Finally, based on these findings, a multidimensional optimization strategy is proposed to enhance the overall performance of the model. The achievements of this research not only provide important guidance for the design and optimization of Quantum−Classical Hybrid Convolutional Neural Networks but also offer new research perspectives for researchers in the field of quantum machine learning.

Physica ScriptaNov 22, 20242 citations

A Project Submitted to the Graduate Faculty of the State University of New York Polytechnic Institute in Partial Fulfillment of the Requirements for the Degree of Master of Science Utica, New York

Hussam Muhammad Anwar

This project compares classical, quantum, and hybrid neural network architectures for multiclass classification on the MNIST and CIFAR10 datasets. The models include a classical convolutional network, two pure quantum neural networks constructed with TorchQuantum, a quanvolutional model that applied fixed random quantum filters to image patches, and hybrid quantum classical networks that combine classical convolution with trainable quantum layers. In addition, a quantum classical quantum convolutional neural network (QCQ-CNN) inspired by recent works is implemented, as well as a separate Qiskit based QCQ-CNN that uses the ZZFeatureMap for data encoding and the RealAmplitudes ansatz for variational processing. Most models were trained under shared hyperparameters and full multiclass supervision, while the Qiskit based QCQ-CNN was trained on a reduced MNIST and CIFAR10 subset in a One-vs-All setting due to the computational cost of simulating quantum circuits. Across both datasets, the classical convolutional neural network achieved the highest accuracy. The pure quantum models performed well and showed small gaps between training and testing accuracy, which suggests that the models did not overfit and were stable. The quanvolutional model produced expressive features but heavily overfit. The TorchQuantum QCQ-CNN achieved lower accuracy than the classical baseline but showed a consistent generalization and avoided the overfitting seen in the quanvolutional mode. The One-vs-All v QCQ-CNN had a strong accuracy for each class, showing that hybrid neural networks can perform well when the task is reduced into smaller subproblems. These results highlight the strengths and weaknesses of current quantum and hybrid neural networks in practical scenarios. The experiments illustrate that shallow quantum circuits can be integrated into classical neural networks to assist in their generalization ability even while the quantum aspects are simulated.

Dec 11, 20250 citations