1887

ITU Journal: ICT Discoveries

The ITU Journal: ICT Discoveries publishes original research on ICT technical developments and their policy and regulatory, economic, social and legal dimensions. It builds bridges between disciplines, connects theory with application, and stimulates international dialogue. This interdisciplinary approach reflects ITU’s comprehensive field of interest and explores the convergence of ICT with other disciplines. It also features review articles, best practice implementation tutorials and case studies. The ITU Journal welcomes submissions at any time, on any topic within its scope.

English

Explainable artificial intelligence

Understanding, visualizing and interpreting deep learning models

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.

English

Keywords: artificial intelligence, sensitivity analysis, interpretability, deep neural networks, black-box models, layer-wise relevance propagation
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error