arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.11166cs.LGcond-mat.stat-mech
收藏

机器学习的特征提取与伊辛模型的相变点

Feature extraction of machine learning and phase transition point of Ising model

Okinawa Institute of Science and Technology(冲绳科学技术大学院大学)

Shotaro Shiba Funai

摘要:

研究了受限玻尔兹曼机(RBM)在不同温度下用伊辛模型的自旋组态训练时提取的特征。利用训练好的RBM,我们得到了自旋组态的迭代重构流(RBM流),并发现在某些情况下RBM流接近Ising模型中的相变点$T=T_c$.由于所提取的特征在重构的配置中被强调,所以在这样的固定点处的配置应该只描述所提取的特征。然后,我们研究了不动点对各种参数的依赖关系,并推测了RBM流的不动点位于相变点的条件。通过分析训练后的RBM的权值矩阵,我们也为该猜想提供了支持证据。

英文摘要:

We study the features extracted by the Restricted Boltzmann Machine (RBM) when it is trained with spin configurations of Ising model at various temperatures. Using the trained RBM, we obtain the flow of iterative reconstructions (RBM flow) of the spin configurations and find that in some cases the flow approaches the phase transition point $T=T_c$ in Ising model. Since the extracted features are emphasized in the reconstructed configurations, the configurations at such a fixed point should describe nothing but the extracted features. Then we investigate the dependence of the fixed point on various parameters and conjecture the condition where the fixed point of the RBM flow is at the phase transition point. We also provide supporting evidence for the conjecture by analyzing the weight matrix of the trained RBM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑