Explainable Neural Networks based on Additive Index Models
This addresses the need for interpretable models in machine learning, particularly for data analysts, but appears incremental as it builds on existing interpretability approaches.
The paper tackles the problem of interpretability in neural networks by introducing the Explainable Neural Network (xNN), which learns interpretable features that can be extracted and displayed straightforwardly, as demonstrated on simulated examples.
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.