arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.06457cs.CVcs.AIstat.ML
收藏

将深层神经网络抽象为概念图以实现概念级解释

Abstracting Deep Neural Networks into Concept Graphs for Concept Level Interpretability

Indian Institute of Technology, Madras(马德拉斯印度理工学院)

Avinash Kori, Parth Natekar, Ganapathy Krishnamurthi, Balaji Srinivasan

摘要:

深度学习模型的黑盒性质使它们在生物医学等领域无法完全信任。大多数可解释性技术并没有捕捉到人类遵循的基于概念的推理。在这项工作中,我们试图通过建立他们学习的概念的图形表示来理解在医学领域执行图像处理任务的训练模型的行为。在抽象的、更高的概念层面上提取模型行为的图形表示将揭示这些模型的学习,并将帮助我们评估模型为预测所采取的步骤。我们提出的两个生物医学问题-脑肿瘤分割和眼底图像分类的实施,我们展示了应用。我们提供了一个替代的图形表示的模型,通过制定一个概念级图如上所述,这使得问题的干预,以找到积极的推理线索更容易处理。理解这些踪迹将提供对模型所遵循的决策过程的层次结构的理解。[As模型的整体性质)。我们的框架可以在https://github.com/koriavinash1/BioExp上找到

英文摘要:

The black-box nature of deep learning models prevents them from being completely trusted in domains like biomedicine. Most explainability techniques do not capture the concept-based reasoning that human beings follow. In this work, we attempt to understand the behavior of trained models that perform image processing tasks in the medical domain by building a graphical representation of the concepts they learn. Extracting such a graphical representation of the model's behavior on an abstract, higher conceptual level would unravel the learnings of these models and would help us to evaluate the steps taken by the model for predictions. We show the application of our proposed implementation on two biomedical problems - brain tumor segmentation and fundus image classification. We provide an alternative graphical representation of the model by formulating a concept level graph as discussed above, which makes the problem of intervention to find active inference trails more tractable. Understanding these trails would provide an understanding of the hierarchy of the decision-making process followed by the model. [As well as overall nature of model]. Our framework is available at https://github.com/koriavinash1/BioExp

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。

↑