Characterizing the Decision Boundary of Deep Neural Networks
Characterizing the Decision Boundary of Deep Neural Networks
复制标题
表征深度神经网络的决策边界
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jiliang Tang
中科院分区：
文献类型：
--
作者：
Hamid Karimi;Tyler Derr;Jiliang Tang
深度神经网络，特别是深度神经分类器，已经成为许多现代应用不可或缺的一部分。尽管它们在实践中取得了成功，但我们对它们如何工作的了解仍然有限，对这种了解的需求正在不断增长。在这方面，深度神经网络分类器可以帮助我们加深对其决策行为的了解的一个关键方面是调查其决策边界。然而，这取决于是否能够访问决策边界附近区域的样本。为了实现这一目标，我们提出了一种新的方法，我们称之为深度决策边界实例生成（DeepDIG）。DeepDIG利用一种基于对抗性示例生成的方法，作为在任何深度神经网络模型的决策边界附近生成样本的有效方法。然后，我们引入了一组重要的原则性特征，这些特征利用决策边界附近生成的实例来提供对深度神经网络的多方面理解。我们在各种深度神经网络模型的多个代表性数据集上进行了广泛的实验，并描述了它们的决策边界。该代码可在此https URL公开获得。
Deep neural networks and in particular, deep neural classifiers have become an integral part of many modern applications. Despite their practical success, we still have limited knowledge of how they work and the demand for such an understanding is evergrowing. In this regard, one crucial aspect of deep neural network classifiers that can help us deepen our knowledge about their decision-making behavior is to investigate their decision boundaries. Nevertheless, this is contingent upon having access to samples populating the areas near the decision boundary. To achieve this, we propose a novel approach we call Deep Decision boundary Instance Generation (DeepDIG). DeepDIG utilizes a method based on adversarial example generation as an effective way of generating samples near the decision boundary of any deep neural network model. Then, we introduce a set of important principled characteristics that take advantage of the generated instances near the decision boundary to provide multifaceted understandings of deep neural networks. We have performed extensive experiments on multiple representative datasets across various deep neural network models and characterized their decision boundaries. The code is publicly available at this https URL.
DOI：
10.1109/tnnls.2018.2886017
发表时间：
2019-09-01
影响因子：
10.4
作者：
Yu, Xiaoyong;He, Pan;Li, Xiaolin
通讯作者：
Li, Xiaolin