Diagnostic classification and symbolic guidance to understand and improve recurrent neural networks

By Dieuwke Hupkes. 2017

Citations in the corpus

• Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract) (2018, unknown): “For a more elaborate analysis of of how diagnostic classifiers can be used to increase insight in the internal dynamics of recurrent neural networks, including gate values, we refer to the work presented by Hupkes and Zuidema (2017).”