A1381
Title: Interpretnn: An R package for statistically-based neural network interpretation
Authors: Andrew McInerney - University of Limerick (Ireland) [presenting]
Kevin Burke - University of Limerick (Ireland)
Abstract: Feedforward neural networks (FNNs) are typically viewed as pure prediction algorithms, and their strong predictive performance has led to their use in many machine-learning applications. Their success in predictivity can be attributed, at least in part, to their ability to capture complex relationships through the modelling of higher-order interactions. However, their flexibility comes with an interpretability trade-off; thus, FNNs have been historically less popular among statisticians, who tend to use more interpretable additive models. Nevertheless, classical statistical theory, such as significance testing and uncertainty quantification, is still relevant for FNNs. Supplementing FNNs with methods of statistical inference, model selection, and covariate-effect visualizations can shift the focus away from black-box prediction and make FNNs more akin to traditional statistical models. This can pave the way towards more inferential analyses. The focus is on the use of the R package, interpretnn, which extends existing neural network objects in R to allow for more statistically-based outputs. The aim of this package is to improve interpretation and to increase the utility of the neural network for statisticians.
