高级检索

大自然的计算:从伊辛模型到生成学习

The computation of nature: from the Ising model to generative learning

  • 摘要: 2024年诺贝尔物理学奖授予约翰·霍普菲尔德和杰弗里·辛顿,这对很多人来说是出乎意料的。文章将从统计物理的视角,从伊辛模型出发,逐步介绍霍普菲尔德和辛顿的主要贡献,其中包括Hopfield模型、玻尔兹曼机、非监督学习,以及现代生成模型。还将回顾统计物理和机器学习在20世纪末期的精彩合作历程,并对未来物理与机器学习交互领域的发展方向进行简单展望。

     

    Abstract: The 2024 Nobel Prize in Physics was awarded to John Hopfield and Geoffrey Hinton, which came as a surprise to many people. In this introductory article, we will explore their major contributions from the perspective of statistical physics, starting with the Ising model. This includes the Hopfield model, Boltzmann machines, unsupervised learning, and modern generative models. The article will also review the exciting collaboration between statistical physics and machine learning at the end of the last century and provide a brief outlook on the future directions of the interdisciplinary field between physics and machine learning.

     

/

返回文章
返回