Neuroevolution under unimodal error landscapes

Bibliographic Details
Main Author: Jagusch, Jan-Benedikt
Publication Date: 2018
Other Authors: Gonçalves, Ivo, Castelli, Mauro
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/46403
Summary: Jagusch, J-B., Gonçalves, I., & Castelli, M. (2018). Neuroevolution under unimodal error landscapes: An exploration of the semantic learning machine algorithm. In GECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion (pp. 159-160). Association for Computing Machinery, Inc. DOI: 10.1145/3205651.3205778
id RCAP_0a8d981c846e7aa8c8ff428c4433782e
oai_identifier_str oai:run.unl.pt:10362/46403
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Neuroevolution under unimodal error landscapesAn exploration of the semantic learning machine algorithmMLPNEATNeuroevolutionSemantic learning machineComputer Science ApplicationsSoftwareComputational Theory and MathematicsTheoretical Computer ScienceJagusch, J-B., Gonçalves, I., & Castelli, M. (2018). Neuroevolution under unimodal error landscapes: An exploration of the semantic learning machine algorithm. In GECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion (pp. 159-160). Association for Computing Machinery, Inc. DOI: 10.1145/3205651.3205778Neuroevolution is a field in which evolutionary algorithms are applied with the goal of evolving Neural Networks (NNs). This paper studies different variants of the Semantic Learning Machine (SLM) algorithm, a recently proposed supervised learning neuroevolution method. Perhaps the most interesting characteristic of SLM is that it searches over unimodal error landscapes in any supervised learning problem where the error is measured as a distance to the known targets. SLM is compared with the NeuroEvolution of Augmenting Topologies (NEAT) algorithm and with a fixed-topology neuroevolution approach. Experiments are performed on a total of 9 real-world regression and classification datasets. The results show that the best SLM variants generally outperform the other neuroevolution approaches in terms of generalization achieved, while also being more efficient in learning the training data. The best SLM variants also outperform the common NN backpropagation-based approach under different topologies. The most efficient SLM variant used in combination with a recently proposed semantic stopping criterion is capable of evolving competitive neural networks in a few seconds on the vast majority of the datasets considered. A final comparison shows that a NN ensemble built with SLM is able to outperform the Random Forest algorithm in two classification datasets.ACM - Association for Computing MachineryNOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNJagusch, Jan-BenediktGonçalves, IvoCastelli, Mauro2018-09-12T22:15:01Z2018-07-062018-07-06T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersion2application/pdfhttp://hdl.handle.net/10362/46403eng9781450357647PURE: 5822890https://doi.org/10.1145/3205651.3205778info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T17:34:45Zoai:run.unl.pt:10362/46403Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:05:51.165856Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Neuroevolution under unimodal error landscapes
An exploration of the semantic learning machine algorithm
title Neuroevolution under unimodal error landscapes
spellingShingle Neuroevolution under unimodal error landscapes
Jagusch, Jan-Benedikt
MLP
NEAT
Neuroevolution
Semantic learning machine
Computer Science Applications
Software
Computational Theory and Mathematics
Theoretical Computer Science
title_short Neuroevolution under unimodal error landscapes
title_full Neuroevolution under unimodal error landscapes
title_fullStr Neuroevolution under unimodal error landscapes
title_full_unstemmed Neuroevolution under unimodal error landscapes
title_sort Neuroevolution under unimodal error landscapes
author Jagusch, Jan-Benedikt
author_facet Jagusch, Jan-Benedikt
Gonçalves, Ivo
Castelli, Mauro
author_role author
author2 Gonçalves, Ivo
Castelli, Mauro
author2_role author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Jagusch, Jan-Benedikt
Gonçalves, Ivo
Castelli, Mauro
dc.subject.por.fl_str_mv MLP
NEAT
Neuroevolution
Semantic learning machine
Computer Science Applications
Software
Computational Theory and Mathematics
Theoretical Computer Science
topic MLP
NEAT
Neuroevolution
Semantic learning machine
Computer Science Applications
Software
Computational Theory and Mathematics
Theoretical Computer Science
description Jagusch, J-B., Gonçalves, I., & Castelli, M. (2018). Neuroevolution under unimodal error landscapes: An exploration of the semantic learning machine algorithm. In GECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion (pp. 159-160). Association for Computing Machinery, Inc. DOI: 10.1145/3205651.3205778
publishDate 2018
dc.date.none.fl_str_mv 2018-09-12T22:15:01Z
2018-07-06
2018-07-06T00:00:00Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/46403
url http://hdl.handle.net/10362/46403
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 9781450357647
PURE: 5822890
https://doi.org/10.1145/3205651.3205778
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 2
application/pdf
dc.publisher.none.fl_str_mv ACM - Association for Computing Machinery
publisher.none.fl_str_mv ACM - Association for Computing Machinery
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596430858584064

Similar Items