Explaining nonlinear classification decisions with deep Taylor decomposition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Montavon, Gregoire | - |
dc.contributor.author | Lapuschkin, Sebastian | - |
dc.contributor.author | Binder, Alexander | - |
dc.contributor.author | Samek, Wojciech | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.date.accessioned | 2021-09-03T06:32:17Z | - |
dc.date.available | 2021-09-03T06:32:17Z | - |
dc.date.created | 2021-06-16 | - |
dc.date.issued | 2017-05 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/83537 | - |
dc.description.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. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.title | Explaining nonlinear classification decisions with deep Taylor decomposition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1016/j.patcog.2016.11.008 | - |
dc.identifier.scopusid | 2-s2.0-85010676902 | - |
dc.identifier.wosid | 000394197700018 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.65, pp.211 - 222 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 65 | - |
dc.citation.startPage | 211 | - |
dc.citation.endPage | 222 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordAuthor | Deep neural networks | - |
dc.subject.keywordAuthor | Heaimapping | - |
dc.subject.keywordAuthor | Taylor decomposition | - |
dc.subject.keywordAuthor | Relevance propagation | - |
dc.subject.keywordAuthor | Image recognition | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.