论文标题
卷积神经网络的信息理论视觉分析框架
An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks
论文作者
论文摘要
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背后的工作机制仍在广泛的讨论和研究中。在对神经网络的理论解释的强烈需求的驱动下，一些研究人员利用信息理论来洞悉黑匣子模型。但是，据我们所知，在可视化社区中，使用信息理论进行定量分析和定性可视化神经网络的神经网络尚未得到广泛研究。在本文中，我们将信息熵和可视化技术结合在一起，以阐明CNN的工作原理。具体而言，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。然后，我们建议在不同情况下计算熵的两种方法。为了从信息理论的角度提供对CNN（例如卷积层，合并层，归一化层）的基本构件的基本理解，我们开发了一个视觉分析系统，CNNSlicer。 CNNSlicer允许用户交互式探索模型内部的信息更改的量。在广泛使用的基准数据集（MNIST和CIFAR-10）的案例研究中，我们证明了系统在打开CNN的BlackBox中的有效性。
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.
