期刊
PHYSICAL REVIEW B
卷 103, 期 12, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevB.103.125117
关键词
-
资金
- National Natural Science Foundation of China [12004205, 11774398, 12047503, 11975294]
- Ministry of Science and Technology of China [2016YFA0300603]
- Key Research Program of Frontier Sciences of CAS [QYZDB-SSW-SYS032]
Tensor networks, originating from quantum physics, have been generalized in machine learning, with PEPS showing superior performance in image classification compared to treelike tensor networks. Furthermore, our model performs as well as multilayer perceptron classifiers with fewer parameters and increased stability.
Tensor networks, a model that originated from quantum physics, has been gradually generalized as efficient models in machine learning in recent years. However, in order to achieve exact contraction, only treelike tensor networks such as the matrix product states and tree tensor networks have been considered, even for modeling two-dimensional data such as images. In this work, we construct supervised learning models for images using the projected entangled pair states (PEPS), a two-dimensional tensor network having a similar structure prior to natural images. Our approach first performs a feature map, which transforms the image data to a product state on a grid, then contracts the product state to a PEPS with trainable parameters to predict image labels. The tensor elements of PEPS are trained by minimizing differences between training labels and predicted labels. The proposed model is evaluated on image classifications using the Modified National Institute of Standards and Technology database (MNIST) and the Fashion-MNIST datasets. We show that our model is significantly superior to existing models using treelike tensor networks. Moreover, using the same input features, our method performs as well as the multilayer perceptron classifier, but with much fewer parameters and is more stable. Our results shed light on potential applications of two-dimensional tensor network models in machine learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据