Deep learning models have gained great popularity in statistical modeling . Theadvantage of deep learning models is that their solutions are difficult tointerpret and explain . We propose a new network architecture that sharessimilar features as generalized linear models, but provides superior predictivepower benefiting from the art of representation learning . This new architecture allows for variable selection of tabular data and for interpretation of thecalibrated deep learning model, in fact, our approach provides an additivedecomposition in the spirit of Shapley values and integrated gradients . Our approach provides a new approach to the study of data in a new way .

Author(s) : Ronald Richman, Mario V. W├╝thrich

Links : PDF - Abstract

Code :

Keywords : learning - deep - approach - models - data -

Leave a Reply

Your email address will not be published. Required fields are marked *