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.
翻译:在许多科学研究领域,从所有输入变量的效果来看,理解和直观黑箱功能对于所有输入变量的效果非常重要。现有的可视化工具不允许一个人同时直观所有输入变量的效果。虽然可以选择一个或两个输入变量,通过 2D 或 3D 绘图可视觉化,同时保持其他变量固定,但这是模型的一个过于简单和不完整的图片。为了克服这一缺陷,我们提出了一个新的可视化方法,使用可解释的建筑神经网络(IANN)来直接和同时直观化所有输入变量的效果。我们提议了两个可解释的结构,每个结构都可以方便地由特定的 IANN 代表,我们讨论一些可能的扩展。我们还提供了一个Python 软件包来实施我们提议的方法。补充材料可以在线查阅。</s>