Litcius/Paper detail

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin, Christopher J. Anders, Klaus‐Robert Müller

2021Proceedings of the IEEE1,321 citationsDOIOpen Access PDF

Abstract

With the broader and highly successful usage of machine learning (ML) in industry and the sciences, there has been a growing demand for explainable artificial intelligence (XAI). Interpretability and explanation methods for gaining a better understanding of the problem-solving abilities and strategies of nonlinear ML, in particular, deep neural networks, are, therefore, receiving increased attention. In this work, we aim to: 1) provide a timely overview of this active emerging field, with a focus on “post hoc” explanations, and explain its theoretical foundations; 2) put interpretability algorithms to a test both from a theory and comparative evaluation perspective using extensive simulations; 3) outline best practice aspects, i.e., how to best include interpretation methods into the standard usage of ML; and 4) demonstrate successful usage of XAI in a representative selection of application scenarios. Finally, we discuss challenges and possible future directions of this exciting foundational field of ML.

Topics & Concepts

InterpretabilityArtificial intelligenceComputer scienceMachine learningField (mathematics)Perspective (graphical)Artificial neural networkInterpretation (philosophy)Deep neural networksSelection (genetic algorithm)Deep learningManagement scienceData scienceEngineeringProgramming languagePure mathematicsMathematicsExplainable Artificial Intelligence (XAI)Adversarial Robustness in Machine LearningMachine Learning and Data Classification
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications | Litcius