Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

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

Authors
Samek, WojciechMontavon, GregoireLapuschkin, SebastianAnders, Christopher J.Mueller, Klaus-Robert
Issue Date
3월-2021
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Black-box models; deep learning; explainable artificial intelligence (XAI); Interpretability; model transparency; neural networks
Citation
PROCEEDINGS OF THE IEEE, v.109, no.3, pp.247 - 278
Indexed
SCIE
SCOPUS
Journal Title
PROCEEDINGS OF THE IEEE
Volume
109
Number
3
Start Page
247
End Page
278
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/128500
DOI
10.1109/JPROC.2021.3060483
ISSN
0018-9219
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.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE