The deep neural network is a widely used framework in machine learning that has been widely applied in various fields. However, deep neural networks often involve a large number of parameters and inputs, many of which may be irrelevant to the goal or true output. These parameters and \textcolor{black}{input variables} not only increase computational complexity, but also contribute to additional computational cost. One solution to this problem is knockoff methods, which have proven successful in controlling false discovery rates in high-dimensional regression. Building on the knockoff methods and using the regularised neural network, this paper proposes three variable screening methods under the condition of controlling false discovery rates: \textit{one layer filter}, \textit{multiple layers filter}, \textit{variable weight aggregation filter}. In comparison with existing algorithms, we find that our algorithms show satisfactory performance.

翻译：深度神经网络是机器学习中广泛使用的框架，已应用于多个领域。然而，深度神经网络通常包含大量参数和输入变量，其中许多可能与目标或真实输出无关。这些参数和输入变量不仅增加计算复杂度，还导致额外的计算成本。解决该问题的一种方法是knockoff方法，该方法在高维回归中已被证明能有效控制伪发现率。本文基于knockoff方法，结合正则化神经网络，提出了三种在控制伪发现率条件下的变量筛选方法：单层过滤器、多层过滤器、变量权重聚合过滤器。与现有算法相比，我们的算法表现出令人满意的性能。