Normalization Influence on ANN-Based Models Performance: A New Proposal for Features’ Contribution Analysis
Date
2021Keywords
Artificial neural networks
Explainability
Feature contribution
Feature normalization
Abstract
Artificial Neural Networks (ANNs) are weighted directed graphs of interconnected neurons widely employed to model complex problems. However, the selection of the optimal ANN architecture and its training parameters is not enough to obtain reliable models. The data preprocessing stage is fundamental to improve the model’s performance. Specifically, Feature Normalisation (FN) is commonly utilised to remove the features’ magnitude aiming at equalising the features’ contribution to the model training. Nevertheless, this work demonstrates that the FN method selection affects the model performance. Also, it is well-known that ANNs are commonly considered a “black box” due to their lack of interpretability. In this sense, several works aim to analyse the features’ contribution to the network for estimating the output. However, these methods, specifically those based on network’s weights, like Garson’s or Yoon’s methods, do not consider preprocessing factors, such as dispersion factors , previously ...
Type
journal article