Understanding, visualizing and interpreting deep learning models Samek, Wojciech creator Wiegand, Thomas Müller, Klaus-Robert text Geneva International Telecommunication Union 2017 monographic eng pdf 10 p. With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching, or even exceeding, the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of their nested non-linear structure, these highly successful machine learning and artificial intelligence models are usually applied in a black-box manner, i.e. no information is provided about what exactly makes them arrive at their predictions. Since this lack of transparency can be a major drawback, e.g. in medical applications, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This paper summarizes recent developments in this field and makes a plea for more interpretability in artificial intelligence. Furthermore, it presents two approaches to explaining predictions of deep learning models, one method which computes the sensitivity of the prediction with respect to changes in the input and one approach which meaningfully decomposes the decision in terms of the input variables. These methods are evaluated on three classification tasks. Wojciech Samek, Thomas Wiegand and Klaus-Robert Müller Tecnologías habilitadoras digitales Science and Technology 2616-8375 Vol. 2018, no. 1, p. 39-48 2018 1 39 https://www.itu.int/dms_pub/itu-s/opb/journal/S-JOURNAL-ICTS.V1I1-2017-5-PDF-E.pdf https://www.itu.int/dms_pub/itu-s/opb/journal/S-JOURNAL-ICTS.V1I1-2017-5-PDF-E.pdf FR-PaOEC 190601 20211006062616.0 00005315