Towards explaining anomalies: A deep Taylor decomposition of one-class models
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kauffmann, Jacob | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.contributor.author | Montavon, Gregoire | - |
dc.date.accessioned | 2021-08-31T01:09:49Z | - |
dc.date.available | 2021-08-31T01:09:49Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2020-05 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/56110 | - |
dc.description.abstract | Detecting anomalies in the data is a common machine learning task, with numerous applications in the sciences and industry. In practice, it is not always sufficient to reach high detection accuracy, one would also like to be able to understand why a given data point has been predicted to be anomalous. We propose a principled approach for one-class SVMs (OC-SVM), that draws on the novel insight that these models can be rewritten as distance/pooling neural networks. This 'neuralization' step lets us apply deep Taylor decomposition (DTD), a methodology that leverages the model structure in order to quickly and reliably explain decisions in terms of input features. The proposed method (called 'OC-DTD') is applicable to a number of common distance-based kernel functions, and it outperforms baselines such as sensitivity analysis, distance to nearest neighbor, or edge detection. (C) 2020 The Authors. Published by Elsevier Ltd. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.subject | NEURAL-NETWORK | - |
dc.subject | SUPPORT VECTOR | - |
dc.subject | VISUALIZATION | - |
dc.title | Towards explaining anomalies: A deep Taylor decomposition of one-class models | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1016/j.patcog.2020.107198 | - |
dc.identifier.scopusid | 2-s2.0-85078086602 | - |
dc.identifier.wosid | 000525824600010 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.101 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 101 | - |
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.keywordPlus | NEURAL-NETWORK | - |
dc.subject.keywordPlus | SUPPORT VECTOR | - |
dc.subject.keywordPlus | VISUALIZATION | - |
dc.subject.keywordAuthor | Outlier detection | - |
dc.subject.keywordAuthor | Explainable machine learning | - |
dc.subject.keywordAuthor | Deep Taylor decomposition | - |
dc.subject.keywordAuthor | Kernel machines | - |
dc.subject.keywordAuthor | Unsupervised learning | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
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.