A neural network is locally specialized to the extent that parts of its computational graph (i.e. structure) can be abstractly represented as performing some comprehensible sub-task relevant to the overall task (i.e. functionality). Are modern deep neural networks locally specialized? How can this be quantified? In this paper, we consider the problem of taking a neural network whose neurons are partitioned into clusters, and quantifying how functionally specialized the clusters are. We propose two proxies for this: importance, which reflects how crucial sets of neurons are to network performance; and coherence, which reflects how consistently their neurons associate with features of the inputs. To measure these proxies, we develop a set of statistical methods based on techniques conventionally used to interpret individual neurons. We apply the proxies to partitionings generated by spectrally clustering a graph representation of the network's neurons with edges determined either by network weights or correlations of activations. We show that these partitionings, even ones based only on weights (i.e. strictly from non-runtime analysis), reveal groups of neurons that are important and coherent. These results suggest that graph-based partitioning can reveal local specialization and that statistical methods can be used to automatedly screen for sets of neurons that can be understood abstractly.
翻译:神经网络是局部专门化的, 以至于其计算图( e. 结构) 的某些部分可以抽象地表现为执行与总体任务( 功能) 相关的某些可理解子任务( 功能) 。 现代深层神经网络是本地专门化的吗? 如何量化? 在本文件中, 我们考虑对神经元被分割成集群的神经网络进行神经网络分析的问题, 并量化这些集群的功能性专业化程度。 我们为此建议了两个方面: 重要性, 它反映了神经元对网络性能的至关重要性; 一致性, 它反映了神经元与投入特征的一贯性关联性。 为了测量这些代理性, 我们开发了一套基于通常用于解释单个神经元的技术的统计方法。 我们应用了光谱组合生成网络神经元的图形代表产生的分解方法, 其边缘由网络重量或激活的关联性决定。 我们显示这些分解方法, 即使是仅基于重量( 严格地从非运行时间分析中) ; 显示神经元与输入输入输入的特性的特性组群, 能够以自动化的分解为重要和连贯的分解。 这些分解方法可以显示, 。 这些分解方法可以显示, 能够显示, 以自动化的分解方法可以显示, 以自动化的分解方法可以显示, 。