Multi-Class Quantum Convolutional Neural Networks

被引：0
作者：
Mordacci, Marco [1 ]
Ferrari, Davide [1 ]
Amoretti, Michele [1 ]
机构：
[1] Univ Parma, Parma, Italy
来源：
PROCEEDINGS OF THE ACM ON WORKSHOP ON QUANTUM SEARCH AND INFORMATION RETRIEVAL, QUASAR 2024 | 2024年
关键词：
Quantum Machine Learning; Classification; Quantum Neural Network;
D O I：
10.1145/3660318.3660326
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Classification is particularly relevant to Information Retrieval, as it is used in various subtasks of the search pipeline. In this work, we propose a quantum convolutional neural network (QCNN) for multi-class classification of classical data. The model is implemented using PennyLane. The optimization process is conducted by minimizing the cross-entropy loss through parameterized quantum circuit optimization. The QCNN is tested on the MNIST dataset with 4, 6, 8 and 10 classes. The results show that with 4 classes, the performance is slightly lower compared to the classical CNN, while with a higher number of classes, the QCNN outperforms the classical neural network.
引用
收藏
页码：9 / 16
页数：8
相关论文
共 26 条
[1]   The power of quantum neural networks [J].
Abbas, Amira ;
Sutter, David ;
Zoufal, Christa ;
Lucchi, Aurelien ;
Figalli, Alessio ;
Woerner, Stefan .
NATURE COMPUTATIONAL SCIENCE, 2021, 1 (06) :403-409
[2]   Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning [J].
Bokhan, Denis ;
Mastiukova, Alena S. ;
Boev, Aleksey S. ;
Trubnikov, Dmitrii N. ;
Fedorov, Aleksey K. .
FRONTIERS IN PHYSICS, 2022, 10
[3]   Generalization in quantum machine learning from few training data [J].
Caro, Matthias C. ;
Huang, Hsin-Yuan ;
Cerezo, M. ;
Sharma, Kunal ;
Sornborger, Andrew ;
Cincio, Lukasz ;
Coles, Patrick J. .
NATURE COMMUNICATIONS, 2022, 13 (01)
[4]   Challenges and opportunities in quantum machine learning [J].
Cerezo, M. ;
Verdon, Guillaume ;
Huang, Hsin-Yuan ;
Cincio, Lukasz ;
Coles, Patrick J. .
NATURE COMPUTATIONAL SCIENCE, 2022, 2 (09) :567-576
[5]   A hybrid classical-quantum approach for multi-class classification [J].
Chalumuri, Avinash ;
Kune, Raghavendra ;
Manoj, B. S. .
QUANTUM INFORMATION PROCESSING, 2021, 20 (03)
[6]   Seeking quantum advantage for neural networks [J].
Coles, Patrick J. .
NATURE COMPUTATIONAL SCIENCE, 2021, 1 (06) :389-390
[7]   Quantum convolutional neural networks [J].
Cong, Iris ;
Choi, Soonwon ;
Lukin, Mikhail D. .
NATURE PHYSICS, 2019, 15 (12) :1273-+
[8]  
Gil-Fuster E, 2024, Arxiv, DOI arXiv:2306.13461
[9]   Quantum Natural Language Processing: Challenges and Opportunities [J].
Guarasci, Raffaele ;
De Pietro, Giuseppe ;
Esposito, Massimo .
APPLIED SCIENCES-BASEL, 2022, 12 (11)
[10]   Quantum convolutional neural network for classical data classification [J].
Hur, Tak ;
Kim, Leeseok ;
Park, Daniel K. .
QUANTUM MACHINE INTELLIGENCE, 2022, 4 (01)
123