Publikation

TSXplain: Demystification of DNN Decisions for Time-Series Using Natural Language and Statistical Features

Mohsin Munir, Shoaib Ahmed Siddiqui, Ferdinand Küsters, Dominique Mercier, Andreas Dengel, Sheraz Ahmed

In: ICANN. International Conference on Artificial Neural Networks (ICANN-2019) September 17-19 Munich Germany Seiten 426-439 11731 ISBN 978-3-030-30493-5 Springer, Cham 9/2019.

Abstrakt

Neural networks (NN) are considered as black boxes due to the lack of explainability and transparency of their decisions. This significantly hampers their deployment in environments where explainability is essential along with the accuracy of the system. Recently, significant efforts have been made for the interpretability of these deep networks with the aim to open up the black box. However, most of these approaches are specifically developed for visual modalities. In addition, the interpretations provided by these systems require expert knowledge and understanding of intelligibility. This indicates a vital gap between the explainability provided by the systems and the novice user. To bridge this gap, we present a novel framework i.e. Time-Series eXplanation (TSXplain) system which produces a natural language based explanation of the decision taken by a NN. It uses the extracted statistical features to describe the decision of a NN, merging the deep learning world with that of statistics. The two-level explanation provides an ample description of the decision made by the network to aid an expert as well as a novice user alike. Our survey and reliability assessment test confirm that the generated explanations are meaningful and correct. We believe that generating natural language based descriptions of the network’s decisions is a big step towards opening up the black box.

TSXplain_ICANN_MUNIR.pdf (pdf, 2 MB)

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence