We constructively prove that every deep ReLU network can be rewritten as a functionally identical three-layer network with weights valued in the extended reals. Based on this proof, we provide an algorithm that, given a deep ReLU network, finds the explicit weights of the corresponding shallow network. The resulting shallow network is transparent and used to generate explanations of the model s behaviour.

翻译：我们构造性地证明了每个深度ReLU网络都可以重写为功能等价的三层网络，其权重取值于扩展实数集。基于此证明，我们提出了一种算法，给定任意深度ReLU网络，能够找到对应浅层网络的显式权重。由此得到的浅层网络具有透明性，可用于生成模型行为的解释。