论文标题
受限的鲍尔茨曼机器，最新进展和平均场理论
Restricted Boltzmann Machine, recent advances and mean-field theory
论文作者
论文摘要
本评论涉及统计物理学的限制性玻尔兹曼机器（RBM）。 RBM是一个经典的机器学习家族（ML）模型，在深度学习的发展中起着核心作用。将其视为一种自旋玻璃模型，并与其他统计物理学模型展示了各种联系，我们收集了在这种情况下涉及平均场理论的最新结果。首先，可以通过对RBM的各种统计组合获得的相图分析RBM的功能，尤其是识别{\ it组成相}，其中将少量的特征或模式组合在一起以形成复杂的模式。然后，我们讨论了能够设计基于均值的学习算法的最新作品。能够从某些{\ IT集合动力学方程}或/和/和/和/和/和线性稳定性参数中重现学习过程的通用方面。
This review deals with Restricted Boltzmann Machine (RBM) under the light of statistical physics. The RBM is a classical family of Machine learning (ML) models which played a central role in the development of deep learning. Viewing it as a Spin Glass model and exhibiting various links with other models of statistical physics, we gather recent results dealing with mean-field theory in this context. First the functioning of the RBM can be analyzed via the phase diagrams obtained for various statistical ensembles of RBM leading in particular to identify a {\it compositional phase} where a small number of features or modes are combined to form complex patterns. Then we discuss recent works either able to devise mean-field based learning algorithms; either able to reproduce generic aspects of the learning process from some {\it ensemble dynamics equations} or/and from linear stability arguments.
