Methods for interpreting and understanding deep neural networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Montavon, Gregoire | - |
dc.contributor.author | Samek, Wojciech | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.date.accessioned | 2021-09-02T15:13:27Z | - |
dc.date.available | 2021-09-02T15:13:27Z | - |
dc.date.created | 2021-06-16 | - |
dc.date.issued | 2018-02 | - |
dc.identifier.issn | 1051-2004 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/77468 | - |
dc.description.abstract | This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. As a tutorial paper, the set of methods covered here is not exhaustive, but sufficiently representative to discuss a number of questions in interpretability, technical challenges, and possible applications. The second part of the tutorial focuses on the recently proposed layer-wise relevance propagation (LRP) technique, for which we provide theory, recommendations, and tricks, to make most efficient use of it on real data. (C) 2017 The Authors. Published by Elsevier Inc. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ACADEMIC PRESS INC ELSEVIER SCIENCE | - |
dc.subject | CLASSIFICATION | - |
dc.subject | PREDICTION | - |
dc.title | Methods for interpreting and understanding deep neural networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1016/j.dsp.2017.10.011 | - |
dc.identifier.scopusid | 2-s2.0-85033371689 | - |
dc.identifier.wosid | 000422703400001 | - |
dc.identifier.bibliographicCitation | DIGITAL SIGNAL PROCESSING, v.73, pp.1 - 15 | - |
dc.relation.isPartOf | DIGITAL SIGNAL PROCESSING | - |
dc.citation.title | DIGITAL SIGNAL PROCESSING | - |
dc.citation.volume | 73 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 15 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | CLASSIFICATION | - |
dc.subject.keywordPlus | PREDICTION | - |
dc.subject.keywordAuthor | Deep neural networks | - |
dc.subject.keywordAuthor | Activation maximization | - |
dc.subject.keywordAuthor | Sensitivity analysis | - |
dc.subject.keywordAuthor | Taylor decomposition | - |
dc.subject.keywordAuthor | Layer-wise relevance propagation | - |
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.