机器学习在相变中的应用

Machine learning applications in phase transitions

机器学习中的神经网络模型,具有强大的数据分类和图形识别功能,在统计物理尤其是相变领域得到了非常广泛的应用.本文综述了近年来机器学习算法在主要相变模型中的应用进展.首先,介绍了主流机器学习算法的背景知识,及应用在平衡相变中的开创性工作.其次,以一个典型的非平衡相变模型——有向逾渗为例,详细介绍了课题组运用监督、无监督和半监督学习在相分类、临界点预测、临界指数测量的一些最新研究结果.接着阐述了机器学习算法在量子多体、软物质物理以及高能物理等领域中相变研究的相关工作.最后进行了相应讨论与展望.

Neural networks in machine learning are highly capable of classifying data and recognizing graphics,and have been widely used in statistical physics,particularly in phase transitions.In this paper,we review recent developments in machine learning algorithms in the application of primary phase transition models.We first introduce the background of modern machine learning algorithms and related pioneering work in equilibrium phase transitions.Second,by taking directed percolation as an example of a typical non-equilibrium phase transition model,we present some of the latest research findings of our group.The research involves supervised,unsupervised,and semi-supervised learning for classifying phases,predicting critical points,and measuring critical exponents.Thereafter,we elaborate on related work on machine learning algorithms in phase transition research in quantum many-body theory,soft matter physics,and high-energy physics.Lastly,corresponding discussions and prospects are presented.