Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm

Bibliographic Details
Main Author: Jagusch, Jan-Benedikt
Publication Date: 2018
Format: Master thesis
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/64813
Summary: Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
id RCAP_64200d79747e44cae75e18aee545eb9f
oai_identifier_str oai:run.unl.pt:10362/64813
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 landscapes : an exploration of the semantic learning machine algorithmSemantic Learning MachineNEATNeuroevolutionDissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business IntelligenceNeuroevolution is a field in which evolutionary algorithms are applied with the goal of evolving Artificial Neural Networks (ANNs). These evolutionary approaches can be used to evolve ANNs with fixed or dynamic topologies. This paper studies the Semantic Learning Machine (SLM) algorithm, a recently proposed neuroevolution method that 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 topology-changing algorithm NeuroEvolution of Augmenting Topologies (NEAT) and with a fixed-topology neuroevolution approach. Experiments are performed on a total of 6 real-world datasets of classification and regression tasks. The results show that the best SLM variants outperform the other neuroevolution approaches in terms of generalization achieved, while also being more efficient in learning the training data. Further comparisons show that the best SLM variants also outperform the common ANN backpropagation-based approach under different topologies. A combination of the SLM with a recently proposed semantic stopping criterion also shows that it is possible to evolve competitive neural networks in a few seconds on the vast majority of the datasets considered.Neuro evolução é uma área onde algoritmos evolucionários são aplicados com o objetivo de evoluir Artificial Neural Networks (ANN). Estas abordagens evolucionárias podem ser utilizadas para evoluir ANNs com topologias fixas ou dinâmicas. Este artigo estuda o algoritmo de Semantic Learning Machine (SLM), um método de neuro evolução proposto recentemente que percorre paisagens de erros unimodais em qualquer problema de aprendizagem supervisionada, onde o erro é medido como a distância com os alvos conhecidos previamente. SLM é comparado com o algoritmo de alteração de topologias NeuroEvolution of Augmenting Topologies (NEAT) e com uma abordagem neuro evolucionária de topologias fixas. Experiências são realizadas em 6 datasets reais de tarefas de regressão e classificação. Os resultados mostram que as melhores variantes de SLM são mais capazes de generalizar quando comparadas com outras abordagens de neuro evolução, ao mesmo tempo que são mais eficientes no processo de treino. Mais comparações mostram que as melhores variantes de SLM são mais eficazes que as abordagens mais comuns de treino de ANN usando diferentes topologias e retro propagação. A combinação de SLM com um critério semântico de paragem do processo de treino também mostra que é possível criar redes neuronais competitivas em poucos segundos, na maioria dos datasets considerados.Castelli, MauroRUNJagusch, Jan-Benedikt2019-03-28T17:11:13Z2018-11-302018-11-30T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/64813TID:202207676enginfo: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:RCAAP2024-05-22T17:38:14Zoai:run.unl.pt:10362/64813Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:09:24.822968Repositórios 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 : an exploration of the semantic learning machine algorithm
spellingShingle Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
Jagusch, Jan-Benedikt
Semantic Learning Machine
NEAT
Neuroevolution
title_short Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
title_full Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
title_fullStr Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
title_full_unstemmed Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
title_sort Neuroevolution under unimodal error landscapes : an exploration of the semantic learning machine algorithm
author Jagusch, Jan-Benedikt
author_facet Jagusch, Jan-Benedikt
author_role author
dc.contributor.none.fl_str_mv Castelli, Mauro
RUN
dc.contributor.author.fl_str_mv Jagusch, Jan-Benedikt
dc.subject.por.fl_str_mv Semantic Learning Machine
NEAT
Neuroevolution
topic Semantic Learning Machine
NEAT
Neuroevolution
description Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
publishDate 2018
dc.date.none.fl_str_mv 2018-11-30
2018-11-30T00:00:00Z
2019-03-28T17:11:13Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/64813
TID:202207676
url http://hdl.handle.net/10362/64813
identifier_str_mv TID:202207676
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
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_ 1833596474420625408

Similar Items