A statistical ensemble of neural networks can be described in terms of a quantum field theory (NN-QFT correspondence). The infinite-width limit is mapped to a free field theory, while finite N corrections are mapped to interactions. After reviewing the correspondence, we will describe how to implement renormalization in this context and discuss preliminary numerical results for translation-invariant kernels. A major outcome is that changing the standard deviation of the neural network weight distribution corresponds to a renormalization flow in the space of networks.
翻译:可以用量子场理论(NN-QFT 函文)来描述神经网络的统计集合。无限宽限被映射为自由场理论,而有限的N校正则被映射为互动。在回顾函文后,我们将描述如何在此背景下实施重新整顿,并讨论翻译不易变内核的初步数字结果。一个主要结果是改变神经网络重量分布的标准偏差与网络空间的重新整顿相对应。