Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models.

翻译：神经网络场论（NN-FTs）通过指定网络架构和网络参数的先验分布，提供了一种构建任意场论（包括共形场论）的新颖方法。在这项工作中，我们提出了一种在这些NN-FTs中构建共形不变缺陷的形式化方法。我们在两个NN标量场论的玩具模型中演示了这一新形式。我们为这些模型中两点关联函数的缺陷算子乘积展开（OPE）类展开，发展了一种基于神经网络的解释。