论文标题
深度神经网络作为复杂网络
Deep Neural Networks as Complex Networks
论文作者
论文摘要
从物理的角度来看，深度神经网络的图形是其“链接”和“顶点”迭代处理数据并以优选求解任务的图形。我们使用复杂的网络理论（CNT）作为定向的加权图代表深神经网络（DNN）：在此框架内，我们引入指标将DNN作为动力学系统研究，其粒度从重量到包括神经元在内的层次跨度。 CNT区分参数和神经元数量不同的网络，隐藏层和激活的类型以及客观任务。我们进一步表明，我们的指标会区分低性能网络与高性能网络。 CNT是一种理论DNN的综合方法，也是一种互补的方法来解释模型的行为，该模型的行为是基于网络理论的，并且超越了研究良好的输入输出关系。
Deep Neural Networks are, from a physical perspective, graphs whose `links` and `vertices` iteratively process data and solve tasks sub-optimally. We use Complex Network Theory (CNT) to represents Deep Neural Networks (DNNs) as directed weighted graphs: within this framework, we introduce metrics to study DNNs as dynamical systems, with a granularity that spans from weights to layers, including neurons. CNT discriminates networks that differ in the number of parameters and neurons, the type of hidden layers and activations, and the objective task. We further show that our metrics discriminate low vs. high performing networks. CNT is a comprehensive method to reason about DNNs and a complementary approach to explain a model's behavior that is physically grounded to networks theory and goes beyond the well-studied input-output relation.
