arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.04247cs.LGcs.AI
收藏

基于一般模式理论的卷积神经网络可解释性

Convolutional Neural Network Interpretability with General Pattern Theory

Nanyang Technological University(南洋理工大学);Alibaba Inc(阿里巴巴集团)

Erico Tjoa, Guan Cuntai

摘要:

正在进行的理解深度神经网络(DNN)的努力提供了许多见解,但DNN仍然没有完全理解。提高DNN的可解释性具有实际好处,例如更负责任的使用,更好的算法维护和改进。数据集结构的复杂性可能导致DNN的黑盒机制难以解决可解释性问题。因此,我们建议使用Ulf Grenander制定的模式理论,其中数据可以被描述为基本对象的配置,使我们能够以组件方式研究卷积神经网络(CNN)的可解释性。具体来说,通过将扩展块(EB)附加到ResNet来形成类似于U-Net的结构,允许其在其EB输出通道处执行类似于语义分割的任务,该EB输出通道被设计为与模式理论的配置兼容。通过这些模块,将展示一些基于热图的可解释人工智能(XAI)方法,以提取构成单个数据样本的各个生成器的解释,从而潜在地降低数据集的复杂性对可解释性问题的影响。包含模式理论元素的MNIST等效数据集旨在促进更顺利地进入这个框架,理论的生成方面自然呈现。

英文摘要:

Ongoing efforts to understand deep neural networks (DNN) have provided many insights, but DNNs remain incompletely understood. Improving DNN's interpretability has practical benefits, such as more accountable usage, better algorithm maintenance and improvement. The complexity of dataset structure may contribute to the difficulty in solving interpretability problem arising from DNN's black-box mechanism. Thus, we propose to use pattern theory formulated by Ulf Grenander, in which data can be described as configurations of fundamental objects that allow us to investigate convolutional neural network's (CNN) interpretability in a component-wise manner. Specifically, U-Net-like structure is formed by attaching expansion blocks (EB) to ResNet, allowing it to perform semantic segmentation-like tasks at its EB output channels designed to be compatible with pattern theory's configurations. Through these modules, some heatmap-based explainable artificial intelligence (XAI) methods will be shown to extract explanations w.r.t individual generators that make up a single data sample, potentially reducing the impact of dataset's complexity to interpretability problem. The MNIST-equivalent dataset containing pattern theory's elements is designed to facilitate smoother entry into this framework, along which the theory's generative aspect is naturally presented.

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。

↑