We explore alternative experimental setups for the iterative sampling (flow) from Restricted Boltzmann Machines (RBM) mapped on the temperature space of square lattice Ising models by a neural network thermometer. This framework has been introduced to explore connections between RBM-based deep neural networks and the Renormalization Group (RG). It has been found that, under certain conditions, the flow of an RBM trained with Ising spin configurations approaches in the temperature space a value around the critical one: $ k_B T_c / J \approx 2.269$. In this paper we consider datasets with no information about model topology to argue that a neural network thermometer is not an accurate way to detect whether the RBM has learned scale invariance or not.
翻译:我们探索了由神经网络温度计在平板Ising模型温度空间上绘制的来自限制波尔兹曼机器(RBM)的迭代取样(流程)的替代实验设置。 这个框架被引入以探索基于成果管理制的深神经网络和再恢复小组(RG)之间的联系。 人们发现,在某些条件下,在温度空间里接受过使用Ising 旋转配置方法培训的成果管理制的流动是关键空间周围的值: $k_B T_c / J \ approx 2.269$。 在本文中,我们认为没有模型地形学信息的数据集可以证明一个神经网络的温度计并不是检测成果管理制是否学习了规模变化的准确方法。