Machine Learning algorithms are increasingly being used in recent years due to their flexibility in model fitting and increased predictive performance. However, the complexity of the models makes them hard for the data analyst to interpret the results and explain them without additional tools. This has led to much research in developing various approaches to understand the model behavior. In this paper, we present the Explainable Neural Network (xNN), a structured neural network designed especially to learn interpretable features. Unlike fully connected neural networks, the features engineered by the xNN can be extracted from the network in a relatively straightforward manner and the results displayed. With appropriate regularization, the xNN provides a parsimonious explanation of the relationship between the features and the output. We illustrate this interpretable feature--engineering property on simulated examples.

本文介绍了可解释化神经网络 (Explainable Neural Network，xNN)，它是一种结构化的神经网络，设计特别用于学习可解释的特征。与全连接神经网络不同，xNN 工程化的特征可以相对简单地从网络中提取出来并展示。同时，在适当的正则化下，xNN 提供了关于特征和输出之间关系的精炼解释。我们在模拟实例上展示了这种可解释特征工程化的性质。

基于加法指数模型的可解释神经网络