• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

机器学习中的混淆方案可检测双相变和准长程有序。

Confusion scheme in machine learning detects double phase transitions and quasi-long-range order.

作者信息

Lee Song Sub, Kim Beom Jun

机构信息

Department of Physics, Sungkyunkwan University, Suwon 16419, Republic of Korea.

出版信息

Phys Rev E. 2019 Apr;99(4-1):043308. doi: 10.1103/PhysRevE.99.043308.

DOI:10.1103/PhysRevE.99.043308
PMID:31108697
Abstract

Thanks to the development of machine learning techniques, it has been shown that the supervised learning can be useful to study critical phenomena of various systems. However, the supervised learning cannot be done without labels which require knowledge about critical behavior of the system. To overcome this barrier, unsupervised machine learning methods have been considered and the confusion scheme has been proposed. In this study, we use the confusion scheme of the unsupervised learning and investigate critical behavior of various systems which exhibit single (double) phase transitions with (without) quasi-long-range order. In detail, we choose the two-color Ashkin-Teller model, the XY model, and the eight-state clock model as such systems and snapshots of the spin configurations at various temperatures are collected via Monte Carlo simulations to be used as input data for the unsupervised machine learning. We also put focus on the size dependence of results and validate the availability of the confusion scheme in thermodynamic limit. Our results indicate that the confusion scheme of the unsupervised learning successfully locates the approximate transition points for all models and becomes more accurate as the system size is increased. We also find a characteristic feature of the result which reflects the presence of a quasi-long-range order. We conclude that regardless of the presence of a quasi-long-range order, single and double phase transitions can be detected via the confusion scheme.

摘要

得益于机器学习技术的发展,研究表明监督学习对于研究各种系统的临界现象可能是有用的。然而,没有标签就无法进行监督学习,而标签需要有关系统临界行为的知识。为了克服这一障碍,人们考虑了无监督机器学习方法并提出了混淆方案。在本研究中,我们使用无监督学习的混淆方案,研究各种表现出具有(不具有)准长程序的单(双)相变的系统的临界行为。具体而言,我们选择双色阿什金 - 泰勒模型、XY模型和八态时钟模型作为此类系统,并通过蒙特卡罗模拟收集不同温度下自旋构型的快照,用作无监督机器学习的输入数据。我们还关注结果的尺寸依赖性,并在热力学极限下验证混淆方案的有效性。我们的结果表明,无监督学习的混淆方案成功地找到了所有模型的近似转变点,并且随着系统尺寸的增加变得更加准确。我们还发现了结果的一个特征,它反映了准长程序的存在。我们得出结论,无论是否存在准长程序,都可以通过混淆方案检测单双相变。

相似文献

1
Confusion scheme in machine learning detects double phase transitions and quasi-long-range order.机器学习中的混淆方案可检测双相变和准长程有序。
Phys Rev E. 2019 Apr;99(4-1):043308. doi: 10.1103/PhysRevE.99.043308.
2
Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination.通过无监督机器学习发现相、相变和交叉:批判性审视。
Phys Rev E. 2017 Jun;95(6-1):062122. doi: 10.1103/PhysRevE.95.062122. Epub 2017 Jun 19.
3
Machine learning dynamical phase transitions in complex networks.机器学习在复杂网络中的动态相变。
Phys Rev E. 2019 Nov;100(5-1):052312. doi: 10.1103/PhysRevE.100.052312.
4
Recognition of polymer configurations by unsupervised learning.通过无监督学习识别聚合物构型。
Phys Rev E. 2019 Apr;99(4-1):043307. doi: 10.1103/PhysRevE.99.043307.
5
Machine learning of phase transitions in the percolation and XY models.渗流和XY模型中相变的机器学习
Phys Rev E. 2019 Mar;99(3-1):032142. doi: 10.1103/PhysRevE.99.032142.
6
Learning by confusion approach to identification of discontinuous phase transitions.通过混淆方法学习以识别不连续相变。
Phys Rev E. 2023 Aug;108(2-1):024113. doi: 10.1103/PhysRevE.108.024113.
7
Unsupervised learning of phase transitions: From principal component analysis to variational autoencoders.相变的无监督学习:从主成分分析到变分自编码器。
Phys Rev E. 2017 Aug;96(2-1):022140. doi: 10.1103/PhysRevE.96.022140. Epub 2017 Aug 18.
8
Ashkin-Teller criticality and weak first-order behavior of the phase transition to a fourfold degenerate state in two-dimensional frustrated Ising antiferromagnets.二维受挫伊辛反铁磁体中向四重简并态转变的阿什金 - 泰勒临界性及弱一级相变行为
Phys Rev E. 2017 Jul;96(1-1):012103. doi: 10.1103/PhysRevE.96.012103. Epub 2017 Jul 5.
9
Unsupervised machine learning account of magnetic transitions in the Hubbard model.无监督机器学习对 Hubbard 模型中磁转变的描述。
Phys Rev E. 2018 Jan;97(1-1):013306. doi: 10.1103/PhysRevE.97.013306.
10
Detecting depinning and nonequilibrium transitions with unsupervised machine learning.用无监督机器学习检测脱钉和非平衡转变。
Phys Rev E. 2020 Apr;101(4-1):042101. doi: 10.1103/PhysRevE.101.042101.

引用本文的文献

1
Confusion-Driven Machine Learning of Structural Phases of a Flexible, Magnetic Stockmayer Polymer.基于混淆驱动的柔性磁性斯托克迈尔聚合物结构相的机器学习
J Chem Theory Comput. 2025 Jul 22;21(14):6729-6742. doi: 10.1021/acs.jctc.5c00381. Epub 2025 Jul 8.
2
Three-Phase Confusion Learning.三相性错乱学习
Entropy (Basel). 2025 Feb 14;27(2):199. doi: 10.3390/e27020199.