arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.03393cs.LGcs.HCstat.MEstat.ML
收藏

用于函数可视化的可解释结构神经网络

Interpretable Architecture Neural Networks for Function Visualization

Northwestern University(西北大学)

Shengtong Zhang, Daniel W. Apley

摘要:

在许多科学研究领域,理解和可视化的黑箱函数的所有输入变量的影响是非常重要的。现有的可视化工具不允许同时可视化所有输入变量的影响。虽然可以选择一个或两个输入变量通过2D或3D图进行可视化,同时保持其他变量固定,但这呈现了模型的过度简化和不完整的画面。为了克服这一缺点,我们提出了一种新的可视化方法,使用可解释的架构神经网络(IANN)直接和同时可视化的所有输入变量的影响。我们提出了两个可解释的结构,其中每一个可以方便地表示一个特定的IANN,我们讨论了一些可能的扩展。我们还提供了一个Python包来实现我们提出的方法。补充材料可在网上查阅。

英文摘要:

In many scientific research fields, understanding and visualizing a black-box function in terms of the effects of all the input variables is of great importance. Existing visualization tools do not allow one to visualize the effects of all the input variables simultaneously. Although one can select one or two of the input variables to visualize via a 2D or 3D plot while holding other variables fixed, this presents an oversimplified and incomplete picture of the model. To overcome this shortcoming, we present a new visualization approach using an interpretable architecture neural network (IANN) to visualize the effects of all the input variables directly and simultaneously. We propose two interpretable structures, each of which can be conveniently represented by a specific IANN, and we discuss a number of possible extensions. We also provide a Python package to implement our proposed method. The supplemental materials are available online.

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。

↑