深度神经网络中单元的角色分类
Role Taxonomy of Units in Deep Neural Networks
AI总结：
本文通过引入功能检索测试，将DNNs中的单元按其在训练集和测试集上的功能偏好分为四类，发现这四类单元的比例与DNNs的泛化能力高度相关，从而为良好泛化能力的DNNs提供了标志。
摘要：
识别深度神经网络（DNNs）中网络单元的角色在许多方面至关重要，包括理解DNNs的机制以及建立深度学习与神经科学之间的基本联系。然而，目前尚不清楚具有不同泛化能力的DNNs中的单元会呈现哪些角色。为此，我们通过引入功能检索测试，对DNNs中的单元进行了角色分类，根据单元在训练集和测试集上的功能偏好将其分为四类。我们从两个不同视角证明，这四类单元的比例与DNNs的泛化能力高度相关，并据此给出了具有良好泛化能力的DNNs的标志。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
