Liu, Yuhan and Li, Wen-Jun and Zhang, Xiao and Lewenstein, Maciej and Su, Gang and Ran, Shi-Ju (2021) Entanglement-Based Feature Extraction by Tensor Network Machine Learning. Frontiers in Applied Mathematics and Statistics, 7. ISSN 2297-4687
![[thumbnail of pubmed-zip/versions/1/package-entries/fams-07-716044.pdf]](http://publish7promo.com/style/images/fileicons/text.png)
pubmed-zip/versions/1/package-entries/fams-07-716044.pdf - Published Version
Download (1MB)
Abstract
It is a hot topic how entanglement, a quantity from quantum information theory, can assist machine learning. In this work, we implement numerical experiments to classify patterns/images by representing the classifiers as matrix product states (MPS). We show how entanglement can interpret machine learning by characterizing the importance of data and propose a feature extraction algorithm. We show on the MNIST dataset that when reducing the number of the retained pixels to 1/10 of the original number, the decrease of the ten-class testing accuracy is only O (10–3), which significantly improves the efficiency of the MPS machine learning. Our work improves machine learning’s interpretability and efficiency under the MPS representation by using the properties of MPS representing entanglement.
Item Type: | Article |
---|---|
Subjects: | Euro Archives > Mathematical Science |
Depositing User: | Managing Editor |
Date Deposited: | 24 Apr 2023 03:55 |
Last Modified: | 24 Apr 2024 07:45 |
URI: | http://publish7promo.com/id/eprint/1213 |