arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.05488cs.LGcs.AI
收藏

作为复杂网络的深度神经网络

Deep Neural Networks as Complex Networks

University of Oxford(牛津大学);University of Catania(卡塔尼亚大学);Queen Mary University of London(伦敦玛丽女王大学)

Emanuele La Malfa, Gabriele La Malfa, Claudio Caprioli, Giuseppe Nicosia, Vito Latora

摘要:

从物理角度来看,深度神经网络是一种图形,其“链接”和“顶点”迭代地处理数据并次优地解决任务。我们使用复杂网络理论(CNT)将深度神经网络(DNN)表示为有向加权图:在这个框架内,我们引入度量来研究DNN作为动态系统,粒度从权重到层,包括神经元。CNT区分在参数和神经元的数量、隐藏层和激活的类型以及目标任务方面不同的网络。我们进一步表明,我们的指标区分低与高性能的网络。CNT是一种综合的方法来推理DNN,也是一种补充方法来解释模型的行为,该模型的行为以网络理论为物理基础,并超越了研究充分的输入输出关系。

英文摘要:

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.

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。

↑