期刊
PHYSICAL REVIEW B
卷 97, 期 4, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevB.97.045207
关键词
-
资金
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- Canada Research Chair program
- Perimeter Institute for Theoretical Physics
- National Science Foundation [NSF PHY-1125915]
- NVIDIA Corporation
- government of Canada through Industry Canada
- province of Ontario througdh the Ministry of Research Innovation
Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed-matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further showa single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.
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