Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/39310
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bello, Marilyn | - |
dc.contributor.author | NAPOLES RUIZ, Gonzalo | - |
dc.contributor.author | VANHOOF, Koen | - |
dc.contributor.author | Garcia, Maria M. | - |
dc.contributor.author | Bello, Rafael | - |
dc.date.accessioned | 2023-01-24T07:33:20Z | - |
dc.date.available | 2023-01-24T07:33:20Z | - |
dc.date.issued | 2022 | - |
dc.date.submitted | 2023-01-12T15:08:14Z | - |
dc.identifier.citation | 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), IEEE, | - |
dc.identifier.isbn | 978-1-7281-8671-9 | - |
dc.identifier.issn | 2161-4393 | - |
dc.identifier.uri | http://hdl.handle.net/1942/39310 | - |
dc.description.abstract | Neural networks are considered a black-box model as their strength in modeling complex interactions makes its operation almost impossible to explain. Still, neural networks remain very interesting tools as they have shown promising performance in various classification tasks. Layer-wise relevance propagation is a technique that, based on a propagation approach, is able to explain the predictions obtained by a neural network. In this work, we propose four adaptations of this technique to operate on multi-label neural networks. The proposed methods provide new ways of distributing the relevance between the output layer and the preceding ones. The efficacy of these adaptations is demonstrated after an experimental study. The study is carried out based on existing evaluation criteria in the literature that measure the explanation's quality. These methods are applied to a case study in which a neural network is used to detect secondary coinfections in patients infected with SARS-CoV-2. Overall, the proposed methods provide a post-hoc interpretability stage of the results. | - |
dc.description.sponsorship | The authors would like to sincerely thank the doctors of the Hospital “Comandante Manuel Fajardo Rivero” in the city of Santa Clara, Cuba, who assisted us in the description and medical terminology associated with the case study under consideration. Likewise, in the validation of the results obtained as an expert in the field. This study is supported by the Special Research Fund of Hasselt University. | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE International Joint Conference on Neural Networks (IJCNN) | - |
dc.rights | Copyright 2023 IEEE - All rights reserved. | - |
dc.subject.other | explanation | - |
dc.subject.other | layer-wise relevance propagation | - |
dc.subject.other | neural networks | - |
dc.subject.other | multi-label scenarios | - |
dc.title | Explanation of Multi-Label Neural Networks with Layer-Wise Relevance Propagation | - |
dc.type | Proceedings Paper | - |
local.bibliographicCitation.conferencedate | JUL 18-23, 2022 | - |
local.bibliographicCitation.conferencename | IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC) | - |
local.bibliographicCitation.conferenceplace | Padua, ITALY | - |
local.bibliographicCitation.jcat | C1 | - |
dc.description.notes | Bello, M (corresponding author), Granada Univ, Andalusian Res Inst Data Sci & Computat Intellige, Granada, Spain. | - |
dc.description.notes | mbgarcia@ugr.es; G.R.Napoles@tilburguniversity.edu; | - |
dc.description.notes | koen.vanhoof@uhasselt.be; mmgarcia@uclv.edu.cu; rbellop@uclv.edu.cu | - |
local.publisher.place | 345 E 47TH ST, NEW YORK, NY 10017 USA | - |
local.type.refereed | Refereed | - |
local.type.specified | Proceedings Paper | - |
dc.identifier.doi | 10.1109/IJCNN55064.2022.9892239 | - |
dc.identifier.isi | 000867070902122 | - |
local.provider.type | wosris | - |
local.bibliographicCitation.btitle | 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | - |
local.description.affiliation | [Bello, Marilyn] Granada Univ, Andalusian Res Inst Data Sci & Computat Intellige, Granada, Spain. | - |
local.description.affiliation | [Napoles, Gonzalo] Tilburg Univ, Dept Cognit Sci & Artificial Intelligence, Tilburg, Netherlands. | - |
local.description.affiliation | [Vanhoof, Koen] Hasselt Univ, Fac Business Econ, Hasselt, Belgium. | - |
local.description.affiliation | [Garcia, Maria M.; Bello, Rafael] Cent Univ Las Villas, Dept Comp Sci, Santa Clara, Cuba. | - |
local.uhasselt.international | yes | - |
item.fullcitation | Bello, Marilyn; NAPOLES RUIZ, Gonzalo; VANHOOF, Koen; Garcia, Maria M. & Bello, Rafael (2022) Explanation of Multi-Label Neural Networks with Layer-Wise Relevance Propagation. In: 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), IEEE,. | - |
item.fulltext | With Fulltext | - |
item.contributor | Bello, Marilyn | - |
item.contributor | NAPOLES RUIZ, Gonzalo | - |
item.contributor | VANHOOF, Koen | - |
item.contributor | Garcia, Maria M. | - |
item.contributor | Bello, Rafael | - |
item.accessRights | Open Access | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Explanation of Multi-Label Neural Networks with Layer-Wise Relevance Propagation.pdf Restricted Access | Published version | 1.73 MB | Adobe PDF | View/Open Request a copy |
2022095656.pdf | Peer-reviewed author version | 1.14 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.