Reliability and Interpretability in Science and Deep Learning

In recent years, the question of the reliability of Machine Learning (ML) methods has acquired significant importance, and the analysis of the associated uncertainties has motivated a growing amount of research. However, most of these studies have applied standard error analysis to ML models, and in particular Deep Neural Network (DNN) models, which represent a rather significant departure from standard scientific modelling. It is therefore necessary to integrate the standard error analysis with a deeper epistemological analysis of the possible …

acquired analysis cs.ai cs.lg deep learning deep neural network dnn error importance interpretability machine machine learning ml models network neural network physics.hist-ph question reliability research science standard studies