Explainable Neural Networks based on Additive Index Models [article]

Joel Vaughan, Agus Sudjianto, Erind Brahimi, Jie Chen, Vijayan N. Nair
2018 arXiv   pre-print
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
more » ... lly 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.
arXiv:1806.01933v1 fatcat:2fr6kwqjhreajpz3hp3vtxnxiy