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 1901.09035cs.LGstat.ML
收藏

利用对抗性示例构建可解释的深度神经网络

Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples

Tsinghua National Lab for Information Science and Technology(清华大学信息科学与技术国家实验室);State Key Lab of Intelligent Technology and Systems(智能技术与系统国家重点实验室);Center for Bio-Inspired Computing Research(生物启发计算研究中心);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)

Yinpeng Dong, Fan Bao, Hang Su, Jun Zhu

摘要:

有时,DNN产生结果是不够的。例如,在医疗保健等应用程序中,用户需要了解决策的基本原理。因此,必须开发算法来学习具有良好可解释性的模型(Doshi-Velez 2017)。导致DNN缺乏可解释性的一个重要因素是神经元的模糊性,其中神经元可能会激发各种不相关的概念。这项工作旨在通过减少神经元的模糊性来提高DNN在整个图像空间上的可解释性。本文主要做了以下几个方面的工作:1)提出了一种定量评价网络中神经元一致性水平的度量方法。2)我们发现,通过利用对抗性示例,神经元的学习特征是模糊的。3)我们提出了一种具有一致性损失的对抗训练算法,以提高对抗样本子集上神经元的一致性。

英文摘要:

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with good interpretability (Doshi-Velez 2017). An important factor that leads to the lack of interpretability of DNNs is the ambiguity of neurons, where a neuron may fire for various unrelated concepts. This work aims to increase the interpretability of DNNs on the whole image space by reducing the ambiguity of neurons. In this paper, we make the following contributions: 1) We propose a metric to evaluate the consistency level of neurons in a network quantitatively. 2) We find that the learned features of neurons are ambiguous by leveraging adversarial examples. 3) We propose to improve the consistency of neurons on adversarial example subset by an adversarial training algorithm with a consistent loss.

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。

↑