An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks
An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks
复制标题
DOI：
10.2312/stag.20211486
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Jingyi Shen;Han-Wei Shen
中科院分区：
文献类型：
--
作者：
Jingyi Shen;Han-Wei Shen
尽管卷积神经网络（CNN）在计算机视觉和自然语言处理方面取得了巨大的成功，但CNN背后的工作机制仍处于广泛的讨论和研究之中。由于对神经网络理论解释的强烈需求，一些研究人员利用信息论来深入了解黑箱模型。然而，据我们所知，利用信息论来定量分析和定性可视化神经网络在可视化领域还没有得到广泛的研究。在本文中，我们将联合收割机信息熵和可视化技术结合起来，阐明CNN是如何工作的。具体来说，我们首先引入一个数据模型来组织可以从CNN模型中提取的数据。在此基础上，提出了两种不同情况下熵的计算方法。为了提供对CNN基本构建块的基本理解（例如，卷积层，池化层，归一化层）从信息理论的角度来看，我们开发了一个可视化分析系统，CNNSlicer。CNNSlicer允许用户交互式地探索模型内部的信息变化量。通过对广泛使用的基准数据集（MNIST和CIFAR-10）的案例研究，我们证明了我们的系统在打开CNN黑箱方面的有效性。
Despite the great success of Convolutional Neural Networks (CNNs) in Computer Vision and Natural Language Processing, the working mechanism behind CNNs is still under extensive discussions and research. Driven by a strong demand for the theoretical explanation of neural networks, some researchers utilize information theory to provide insight into the black box model. However, to the best of our knowledge, employing information theory to quantitatively analyze and qualitatively visualize neural networks has not been extensively studied in the visualization community. In this paper, we combine information entropies and visualization techniques to shed light on how CNN works. Specifically, we first introduce a data model to organize the data that can be extracted from CNN models. Then we propose two ways to calculate entropy under different circumstances. To provide a fundamental understanding of the basic building blocks of CNNs (e.g., convolutional layers, pooling layers, normalization layers) from an information-theoretic perspective, we develop a visual analysis system, CNNSlicer. CNNSlicer allows users to interactively explore the amount of information changes inside the model. With case studies on the widely used benchmark datasets (MNIST and CIFAR-10), we demonstrate the effectiveness of our system in opening the blackbox of CNNs.