neuralGAM: An R Package for Fitting Generalized Additive Neural Networks
This provides an interpretable deep learning tool for researchers and practitioners in fields like anomaly detection and disease diagnosis, though it is incremental as it builds on existing Generalized Additive Model concepts.
The paper tackles the black-box problem in neural networks by introducing neuralGAM, an R package that implements Generalized Additive Neural Networks to estimate feature contributions, resulting in a highly accurate and interpretable deep learning model.
Nowadays, Neural Networks are considered one of the most effective methods for various tasks such as anomaly detection, computer-aided disease detection, or natural language processing. However, these networks suffer from the ``black-box'' problem which makes it difficult to understand how they make decisions. In order to solve this issue, an R package called neuralGAM is introduced. This package implements a Neural Network topology based on Generalized Additive Models, allowing to fit an independent Neural Network to estimate the contribution of each feature to the output variable, yielding a highly accurate and interpretable Deep Learning model. The neuralGAM package provides a flexible framework for training Generalized Additive Neural Networks, which does not impose any restrictions on the Neural Network architecture. We illustrate the use of the neuralGAM package in both synthetic and real data examples.