论文标题
深度神经网络中单位的角色分类学
Role Taxonomy of Units in Deep Neural Networks
论文作者
论文摘要
在许多方面，确定网络单元在深神网络（DNN）中的作用至关重要，包括对DNN的机制进行理解，并在深度学习与神经科学之间建立基本联系。但是，仍不清楚具有不同概括能力的DNN中哪些单位的作用。为此，我们通过引入功能检索测试来赋予DNN中单元的角色分类学，该测试将单元分别偏向于单独的训练集和测试集，将单元分为四种类型。我们表明，这四个类别的比率与从两个不同的角度的DNN的概括能力高度相关，基于我们给出具有良好概括的DNN的迹象。
Identifying the role of network units in deep neural networks (DNNs) is critical in many aspects including giving understandings on the mechanisms of DNNs and building basic connections between deep learning and neuroscience. However, there remains unclear on which roles the units in DNNs with different generalization ability could present. To this end, we give role taxonomy of units in DNNs via introducing the retrieval-of-function test, where units are categorized into four types in terms of their functional preference on separately the training set and testing set. We show that ratios of the four categories are highly associated with the generalization ability of DNNs from two distinct perspectives, based on which we give signs of DNNs with well generalization.
