Abstract
This methodological article is mainly aimed at establishing a bridge between classification and regression tasks, in a frame shaped by performance evaluation. More specifically, a general procedure for calculating performance measures is proposed, which can be applied to both classification and regression models. To this end, a notable change in the policy used to evaluate the confusion matrix is made, with the goal of reporting information about regression performance therein. This policy, called generalized token sharing, allows to a) assess models trained on both classification and regression tasks, b) evaluate the importance of input features, and c) inspect the behavior of multilayer perceptrons by looking at their hidden layers. The occurrence of success and failure patterns at the hidden layers of multilayer perceptrons trained and tested on selected regression problems, together with the effectiveness of layer-wise training, is also discussed.
Funder
BBMRI.it (Italian national node of BBMRI-ERIC), which is a research infrastructure financed by the Italian Government and by the Italian Ministry of University and Research
Publisher
Public Library of Science (PLoS)
Reference18 articles.
1. Learning Deep Architectures for AI;Y Bengio;Foundations and Trends in Machine Learning,2009
2. Gunning D. Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA); 2017. DARPA-BAA-16-53.
3. Tishby N, Pereira FC, Bialek W. The information bottleneck method; 2000. Available from: https://arxiv.org/abs/physics/0004057.
4. Opening the Black Box of Deep Neural Networks via Information;R Shwartz-Ziv;CoRR,2017