Detailed Information

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

Explaining nonlinear classification decisions with deep Taylor decomposition

Authors
Montavon, GregoireLapuschkin, SebastianBinder, AlexanderSamek, WojciechMueller, Klaus-Robert
Issue Date
5월-2017
Publisher
ELSEVIER SCI LTD
Keywords
Deep neural networks; Heaimapping; Taylor decomposition; Relevance propagation; Image recognition
Citation
PATTERN RECOGNITION, v.65, pp.211 - 222
Indexed
SCIE
SCOPUS
Journal Title
PATTERN RECOGNITION
Volume
65
Start Page
211
End Page
222
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/83537
DOI
10.1016/j.patcog.2016.11.008
ISSN
0031-3203
Abstract
Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems such as image recognition. Although these methods perform impressively well, they have a significant disadvantage, the lack of transparency, limiting the interpretability of the solution and thus the scope of application in practice. Especially DNNs act as black boxes due to their multilayer nonlinear structure. In this paper we introduce a novel methodology for interpreting generic multilayer neural networks by decomposing the network classification decision into contributions of its input elements. Although our focus is on image classification, the method is applicable to a broad set of input data, learning tasks and network architectures. Our method called deep Taylor decomposition efficiently utilizes the structure of the network by backpropagating the explanations from the output to the input layer. We evaluate the proposed method empirically on the MNIST and ILSVRC data sets.
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