Show simple item record

dc.contributor.authorWalter, M
dc.contributor.authorWalker, D
dc.contributor.authorCraven, M
dc.contributor.editorFieldsend JE
dc.contributor.editorWagner M
dc.date.accessioned2022-05-03T15:50:40Z
dc.date.issued2022-07-19
dc.identifier.isbn9781450392686
dc.identifier.urihttp://hdl.handle.net/10026.1/19155
dc.description.abstract

The comprehension of the Evolutionary Algorithm (EA) search process is often eluded by challenges of transparency inherent to \textit{black-box} EAs, thus affecting algorithm enhancement and hyper-parameter optimisation. In this work, we develop algorithm insight by introducing the Population Dynamics Plot (PopDP). PopDP is a novel and intuitive visualisation capable of visualising the population of solutions, the parent-offspring lineage, solution perturbation operators, and the search process journey. We apply PopDP to NSGA-II to demonstrate the insight attained and the effectiveness of PopDP for visualising algorithm search on a series of discrete dual- and many-objective knapsack problems of different complexities, and our results demonstrate that the method can be used to produce a visualisation in which the lineage of solutions can be clearly seen. We also consider the efficacy of the proposed explainable visualisation against emerging approaches to benchmarking explainable AI methods and consider the accessibility of the resulting visualisations.

dc.format.extent1794-1802
dc.language.isoen
dc.publisherAssociation for Computing Machinery
dc.subjectEvolutionary Computation
dc.subjectExplainability
dc.subjectMany-Objective Optimisation
dc.subjectMulti-Objective Optimisation
dc.subjectVisualisation
dc.titleAn Explainable Visualisation of the Evolutionary Search Process
dc.typeconference
dc.typeProceedings Paper
plymouth.author-urlhttps://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:001035469400281&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=11bb513d99f797142bcfeffcc58ea008
plymouth.date-start2022-07-09
plymouth.date-finish2022-07-13
plymouth.publisher-urlhttp://dx.doi.org/10.1145/3520304.3533984
plymouth.conference-nameECXAI — Evolutionary Computation and Explainable AI Workshop of GECCO 2022
plymouth.publication-statusPublished
plymouth.journalGECCO'22: Proceedings of the Genetic and Evolutionary Computation Conference Companion
dc.identifier.doi10.1145/3520304.3533984
plymouth.organisational-group/Plymouth
plymouth.organisational-group/Plymouth/Faculty of Science and Engineering
plymouth.organisational-group/Plymouth/Faculty of Science and Engineering/School of Engineering, Computing and Mathematics
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA/EXTENDED UoA 10 - Mathematical Sciences
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA/UoA10 Mathematical Sciences
plymouth.organisational-group/Plymouth/REF 2021 Researchers by UoA/UoA11 Computer Science and Informatics
plymouth.organisational-group/Plymouth/Users by role
plymouth.organisational-group/Plymouth/Users by role/Academics
dcterms.dateAccepted2022-04-25
dc.rights.embargodate2022-7-22
rioxxterms.versionAccepted Manuscript
rioxxterms.versionofrecord10.1145/3520304.3533984
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2022-07-09
rioxxterms.typeConference Paper/Proceeding/Abstract


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record


All items in PEARL are protected by copyright law.
Author manuscripts deposited to comply with open access mandates are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author.
Theme by 
Atmire NV