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 2106.04693cs.LGcs.ITcs.NEmath.IT
收藏

关于深度学习架构中神经元社区的进化

On the Evolution of Neuron Communities in a Deep Learning Architecture

University of Saskatchewan(萨斯喀彻温大学)

Sakib Mostafa, Debajyoti Mondal

摘要:

在过去的十年中,深度学习技术越来越多地被用于分类任务,但解释深度学习架构如何实现最先进的性能仍然是一个难以捉摸的目标。虽然所有的训练信息都深深地嵌入到训练模型中,但我们仍然不能仅仅通过分析模型来了解它的性能。本文考察了基于深度学习的分类模型的神经元激活模式,并探讨了模型的性能是否可以通过神经元的激活行为来解释。我们提出两种方法:一种是将神经元的激活行为建模为图形,并检查神经元是否形成有意义的社区,另一种是使用熵来检查神经元行为的可预测性。我们的综合实验研究表明,社区质量和熵可以提供新的见解深度学习模型的性能,从而铺平了一条新的方式来解释深度学习模型直接从神经元的激活模式。

英文摘要:

Deep learning techniques are increasingly being adopted for classification tasks over the past decade, yet explaining how deep learning architectures can achieve state-of-the-art performance is still an elusive goal. While all the training information is embedded deeply in a trained model, we still do not understand much about its performance by only analyzing the model. This paper examines the neuron activation patterns of deep learning-based classification models and explores whether the models' performances can be explained through neurons' activation behavior. We propose two approaches: one that models neurons' activation behavior as a graph and examines whether the neurons form meaningful communities, and the other examines the predictability of neurons' behavior using entropy. Our comprehensive experimental study reveals that both the community quality and entropy can provide new insights into the deep learning models' performances, thus paves a novel way of explaining deep learning models directly from the neurons' activation pattern.

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。

↑