https://scholars.lib.ntu.edu.tw/handle/123456789/606836
標題: | An end-to-end trainable hybrid classical-quantum classifier | 作者: | Chen S.Y.-C Huang C.-M Hsing C.-W Kao Y.-J. YING-JER KAO |
關鍵字: | Principal component analysis; Quantum machine learning; Tensor network; Variational quantum circuit; Classification (of information); Machine learning; Network architecture; Quantum theory; Tensors; Timing circuits; Classical-quantum; End to end; Hybrid model; Network-based; Principal-component analysis; Quantum circuit; Quantum machine learning; Tensor network; Training framework; Variational quantum circuit; Principal component analysis | 公開日期: | 2021 | 卷: | 2 | 期: | 4 | 來源出版物: | Machine Learning: Science and Technology | 摘要: | We introduce a hybrid model combining a quantum-inspired tensor network and a variational quantum circuit to perform supervised learning tasks. This architecture allows for the classical and quantum parts of the model to be trained simultaneously, providing an end-to-end training framework. We show that compared to the principal component analysis, a tensor network based on the matrix product state with low bond dimensions performs better as a feature extractor for the input data of the variational quantum circuit in the binary and ternary classification of MNIST and Fashion-MNIST datasets. The architecture is highly adaptable and the classical-quantum boundary can be adjusted according to the availability of the quantum resource by exploiting the correspondence between tensor networks and quantum circuits. ? 2021 The Author(s). |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115443801&doi=10.1088%2f2632-2153%2fac104d&partnerID=40&md5=393d805aea5f286e6fe6bcf5157a139e https://scholars.lib.ntu.edu.tw/handle/123456789/606836 |
ISSN: | 26322153 | DOI: | 10.1088/2632-2153/ac104d |
顯示於: | 物理學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。