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

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 strategi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the IEEE Ročník 109; číslo 3; s. 247 - 278
Hlavní autoři: Samek, Wojciech, Montavon, Gregoire, Lapuschkin, Sebastian, Anders, Christopher J., Muller, Klaus-Robert
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.03.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Artificial intelligence
Artificial neural networks
Best practice
Best practices
Black-box models
Deep learning
Explainable artificial intelligence
explainable artificial intelligence (XAI)
Interpretability
Machine learning
model transparency
Neural networks
Problem-solving
Systematics
Unsupervised learning
ISSN:0018-9219, 1558-2256
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2021.3060483