Environmental adaptation and differential replication in machine learning

When deployed in the wild, machine learning models are usually confronted withan environment that imposes severe constraints. As this environment evolves, so do these constraints.As a result, the feasible set of solutions for the considered need is prone to change in time. We referto this problem as...

Descripción completa

Detalles Bibliográficos
Autores: Unceta, Irene, Nin, Jordi, Pujol Vila, Oriol
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/174914
Acceso en línea:https://hdl.handle.net/2445/174914
Access Level:acceso abierto
Palabra clave:Aprenentatge automàtic
Selecció natural
Machine learning
Natural selection
id ES_2b8a9054ef7817ac61ea6fd85dbe14d0
oai_identifier_str oai:diposit.ub.edu:2445/174914
network_acronym_str ES
network_name_str España
repository_id_str
spelling Environmental adaptation and differential replication in machine learningUnceta, IreneNin, JordiPujol Vila, OriolAprenentatge automàticSelecció naturalMachine learningNatural selectionWhen deployed in the wild, machine learning models are usually confronted withan environment that imposes severe constraints. As this environment evolves, so do these constraints.As a result, the feasible set of solutions for the considered need is prone to change in time. We referto this problem as that of environmental adaptation. In this paper, we formalize environmentaladaptation and discuss how it differs from other problems in the literature. We propose solutionsbased on differential replication, a technique where the knowledge acquired by the deployed modelsis reused in specific ways to train more suitable future generations. We discuss different mechanismsto implement differential replications in practice, depending on the considered level of knowledge.Finally, we present seven examples where the problem of environmental adaptation can be solvedthrough differential replication in real-life applications.MDPI2020info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2445/174914Articles publicats en revistes (Matemàtiques i Informàtica)reponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaInglésReproducció del document publicat a: https://doi.org/10.3390/e22101122Entropy, 2020, vol. 22, num. 10https://doi.org/10.3390/e22101122cc-by (c) Unceta, Irene et al., 2020http://creativecommons.org/licenses/by/3.0/esinfo:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/1749142026-05-27T06:46:51Z
dc.title.none.fl_str_mv Environmental adaptation and differential replication in machine learning
title Environmental adaptation and differential replication in machine learning
spellingShingle Environmental adaptation and differential replication in machine learning
Unceta, Irene
Aprenentatge automàtic
Selecció natural
Machine learning
Natural selection
title_short Environmental adaptation and differential replication in machine learning
title_full Environmental adaptation and differential replication in machine learning
title_fullStr Environmental adaptation and differential replication in machine learning
title_full_unstemmed Environmental adaptation and differential replication in machine learning
title_sort Environmental adaptation and differential replication in machine learning
dc.creator.none.fl_str_mv Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
author Unceta, Irene
author_facet Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
author_role author
author2 Nin, Jordi
Pujol Vila, Oriol
author2_role author
author
dc.subject.none.fl_str_mv Aprenentatge automàtic
Selecció natural
Machine learning
Natural selection
topic Aprenentatge automàtic
Selecció natural
Machine learning
Natural selection
description When deployed in the wild, machine learning models are usually confronted withan environment that imposes severe constraints. As this environment evolves, so do these constraints.As a result, the feasible set of solutions for the considered need is prone to change in time. We referto this problem as that of environmental adaptation. In this paper, we formalize environmentaladaptation and discuss how it differs from other problems in the literature. We propose solutionsbased on differential replication, a technique where the knowledge acquired by the deployed modelsis reused in specific ways to train more suitable future generations. We discuss different mechanismsto implement differential replications in practice, depending on the considered level of knowledge.Finally, we present seven examples where the problem of environmental adaptation can be solvedthrough differential replication in real-life applications.
publishDate 2020
dc.date.none.fl_str_mv 2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/174914
url https://hdl.handle.net/2445/174914
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Reproducció del document publicat a: https://doi.org/10.3390/e22101122
Entropy, 2020, vol. 22, num. 10
https://doi.org/10.3390/e22101122
dc.rights.none.fl_str_mv cc-by (c) Unceta, Irene et al., 2020
http://creativecommons.org/licenses/by/3.0/es
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by (c) Unceta, Irene et al., 2020
http://creativecommons.org/licenses/by/3.0/es
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv Articles publicats en revistes (Matemàtiques i Informàtica)
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405155703652352
score 15,301603

Similares en LA Referencia