An end-to-end trainable hybrid classical-quantum classifier

Chen, Samuel Yen-Chi and Huang, Chih-Min and Hsing, Chia-Wei and Kao, Ying-Jer (2021) An end-to-end trainable hybrid classical-quantum classifier. Machine Learning: Science and Technology, 2 (4). 045021. ISSN 2632-2153

[thumbnail of Chen_2021_Mach._Learn.__Sci._Technol._2_045021.pdf] Text
Chen_2021_Mach._Learn.__Sci._Technol._2_045021.pdf - Published Version

Download (544kB)

Abstract

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.

Item Type: Article
Subjects: Middle East Library > Multidisciplinary
Depositing User: Unnamed user with email support@middle-eastlibrary.com
Date Deposited: 11 Jul 2023 04:54
Last Modified: 05 Jun 2024 10:19
URI: http://editor.openaccessbook.com/id/eprint/1271

Actions (login required)

View Item
View Item